Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 20.1455. Min Range: -20.1455
Max Act: 20.1455. Min Act: -0.1700
Data Index: 3809891 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 20.1455. Min Range: -20.1455
Max Act: 19.7705. Min Act: -0.1700
Data Index: 5424830 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 20.1455. Min Range: -20.1455
Max Act: 19.7705. Min Act: -0.1700
Data Index: 5178367 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 20.1455. Min Range: -20.1455
Max Act: 19.5205. Min Act: -0.1700
Data Index: 5865210 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 20.1455. Min Range: -20.1455
Max Act: 19.3955. Min Act: -0.1700
Data Index: 6112045 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 20.1455. Min Range: -20.1455
Max Act: 19.0205. Min Act: -0.1700
Data Index: 842211 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 20.1455. Min Range: -20.1455
Max Act: 19.0205. Min Act: -0.1700
Data Index: 5993497 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 20.1455. Min Range: -20.1455
Max Act: 19.0205. Min Act: -0.1700
Data Index: 4122137 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.8955. Min Act: -0.1700
Data Index: 4333617 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.8955. Min Act: -0.1700
Data Index: 2329916 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.8955. Min Act: -0.1700
Data Index: 7793233 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.8955. Min Act: -0.1700
Data Index: 5451932 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.8955. Min Act: -0.1700
Data Index: 1236205 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.7705. Min Act: -0.1700
Data Index: 5529667 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.6455. Min Act: -0.1700
Data Index: 3774841 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.6455. Min Act: -0.1700
Data Index: 1507961 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.5205. Min Act: -0.1700
Data Index: 1220302 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.6455. Min Act: -0.1700
Data Index: 5550285 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.6455. Min Act: -0.1700
Data Index: 6657238 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 20.1455. Min Range: -20.1455
Max Act: 18.5205. Min Act: -0.1700
Data Index: 1006614 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19