Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 905 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.9169. Min Act: -0.1700
Data Index: 1300946 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.7606. Min Act: -0.1700
Data Index: 5054172 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.7606. Min Act: -0.1700
Data Index: 7706828 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.6356. Min Act: -0.1700
Data Index: 7342092 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.6356. Min Act: -0.1700
Data Index: 611450 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.6356. Min Act: -0.1700
Data Index: 3490408 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5376021 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.6044. Min Act: -0.1700
Data Index: 7551357 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.6044. Min Act: -0.1700
Data Index: 7047180 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.5419. Min Act: -0.1700
Data Index: 7379065 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.4481. Min Act: -0.1700
Data Index: 5558175 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.4481. Min Act: -0.1700
Data Index: 8374266 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.4481. Min Act: -0.1700
Data Index: 7237149 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.4169. Min Act: -0.1700
Data Index: 565964 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.4169. Min Act: -0.1700
Data Index: 6570707 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.4169. Min Act: -0.1700
Data Index: 8536427 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.4169. Min Act: -0.1700
Data Index: 6245315 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.3856. Min Act: -0.1700
Data Index: 2627470 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.3856. Min Act: -0.1700
Data Index: 8577356 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9169. Min Range: -5.9169
Max Act: 5.3544. Min Act: -0.1700
Data Index: 3076196 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19