Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4527. Min Range: -9.4527
Max Act: 9.4527. Min Act: -0.1700
Data Index: 4200323 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4527. Min Range: -9.4527
Max Act: 9.0777. Min Act: -0.1700
Data Index: 3155485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.7027. Min Act: -0.1700
Data Index: 4389124 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.8277. Min Act: -0.1700
Data Index: 2245558 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.6402. Min Act: -0.1700
Data Index: 8219880 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.7027. Min Act: -0.1700
Data Index: 2826133 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.5777. Min Act: -0.1700
Data Index: 1006959 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.5777. Min Act: -0.1700
Data Index: 7718978 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.5152. Min Act: -0.1700
Data Index: 3210864 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.5777. Min Act: -0.1700
Data Index: 323522 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.5152. Min Act: -0.1700
Data Index: 6827274 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.5152. Min Act: -0.1700
Data Index: 5274441 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.5152. Min Act: -0.1700
Data Index: 1249236 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.4527. Min Act: -0.1700
Data Index: 307813 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.4527. Min Act: -0.1700
Data Index: 6103068 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.3902. Min Act: -0.1700
Data Index: 5223218 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.3277. Min Act: -0.1700
Data Index: 6327747 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.4527. Min Act: -0.1700
Data Index: 5826860 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.3277. Min Act: -0.1700
Data Index: 4735864 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4527. Min Range: -9.4527
Max Act: 8.2652. Min Act: -0.1700
Data Index: 6793271 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19