Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3339. Min Act: -0.1700
Data Index: 1924233 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3339. Min Act: -0.1700
Data Index: 4163749 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3339. Min Act: -0.1700
Data Index: 8040108 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3339. Min Act: -0.1700
Data Index: 8418426 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3026. Min Act: -0.1700
Data Index: 332025 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3026. Min Act: -0.1700
Data Index: 1386863 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2714. Min Act: -0.1700
Data Index: 2922383 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.3026. Min Act: -0.1700
Data Index: 5380123 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2714. Min Act: -0.1700
Data Index: 7293741 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2089. Min Act: -0.1700
Data Index: 561403 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2089. Min Act: -0.1700
Data Index: 5599305 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2401. Min Act: -0.1700
Data Index: 4102404 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2401. Min Act: -0.1700
Data Index: 3383941 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2089. Min Act: -0.1700
Data Index: 4115074 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.2089. Min Act: -0.1700
Data Index: 3679211 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.1776. Min Act: -0.1700
Data Index: 4190187 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.1776. Min Act: -0.1700
Data Index: 345257 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.1776. Min Act: -0.1700
Data Index: 3861086 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.1776. Min Act: -0.1700
Data Index: 2857816 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3339. Min Range: -5.3339
Max Act: 5.1776. Min Act: -0.1700
Data Index: 2533033 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19