Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.6550. Min Act: -0.1700
Data Index: 3322003 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.5925. Min Act: -0.1700
Data Index: 4688989 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.5300. Min Act: -0.1700
Data Index: 4005302 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.5300. Min Act: -0.1700
Data Index: 3131808 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4362. Min Act: -0.1700
Data Index: 5162397 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4362. Min Act: -0.1700
Data Index: 4257992 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4362. Min Act: -0.1700
Data Index: 3789048 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4362. Min Act: -0.1700
Data Index: 5874028 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4050. Min Act: -0.1700
Data Index: 412516 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4362. Min Act: -0.1700
Data Index: 8191166 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4050. Min Act: -0.1700
Data Index: 761524 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4050. Min Act: -0.1700
Data Index: 7715358 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4362. Min Act: -0.1700
Data Index: 987585 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4050. Min Act: -0.1700
Data Index: 2994779 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.3737. Min Act: -0.1700
Data Index: 6820892 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.3737. Min Act: -0.1700
Data Index: 1634851 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4050. Min Act: -0.1700
Data Index: 7024335 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.3737. Min Act: -0.1700
Data Index: 3382788 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.3737. Min Act: -0.1700
Data Index: 3600942 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6550. Min Range: -5.6550
Max Act: 5.4050. Min Act: -0.1700
Data Index: 7226272 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19