Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2135. Min Range: -7.2135
Max Act: 7.2135. Min Act: -0.1700
Data Index: 4857498 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2135. Min Range: -7.2135
Max Act: 7.1510. Min Act: -0.1700
Data Index: 5806784 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2135. Min Range: -7.2135
Max Act: 7.0885. Min Act: -0.1700
Data Index: 6903229 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2135. Min Range: -7.2135
Max Act: 7.0885. Min Act: -0.1700
Data Index: 7546920 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2135. Min Range: -7.2135
Max Act: 7.0260. Min Act: -0.1700
Data Index: 5791913 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2135. Min Range: -7.2135
Max Act: 7.0260. Min Act: -0.1700
Data Index: 4161222 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.9948. Min Act: -0.1700
Data Index: 8305696 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.9948. Min Act: -0.1700
Data Index: 5659050 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.9635. Min Act: -0.1700
Data Index: 8496647 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.9635. Min Act: -0.1700
Data Index: 4103081 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.9323. Min Act: -0.1700
Data Index: 5312263 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.9323. Min Act: -0.1700
Data Index: 8004922 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8698. Min Act: -0.1700
Data Index: 6022136 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8385. Min Act: -0.1700
Data Index: 8772810 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8073. Min Act: -0.1700
Data Index: 4814902 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8073. Min Act: -0.1700
Data Index: 5995434 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8385. Min Act: -0.1700
Data Index: 3076120 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8073. Min Act: -0.1700
Data Index: 3591160 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8073. Min Act: -0.1700
Data Index: 661549 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2135. Min Range: -7.2135
Max Act: 6.8073. Min Act: -0.1700
Data Index: 2191644 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19