Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.3136. Min Act: -0.1700
Data Index: 5460914 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.2665. Min Act: -0.1700
Data Index: 3313669 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.2665. Min Act: -0.1700
Data Index: 5109894 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.2194. Min Act: -0.1700
Data Index: 1210381 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.2194. Min Act: -0.1700
Data Index: 211962 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.2194. Min Act: -0.1700
Data Index: 1388172 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.2036. Min Act: -0.1700
Data Index: 8308078 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1879. Min Act: -0.1700
Data Index: 2493506 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.2036. Min Act: -0.1700
Data Index: 4581464 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1722. Min Act: -0.1700
Data Index: 832703 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1722. Min Act: -0.1700
Data Index: 5940245 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1564. Min Act: -0.1700
Data Index: 7626690 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1722. Min Act: -0.1700
Data Index: 5560771 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1722. Min Act: -0.1700
Data Index: 6135939 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1722. Min Act: -0.1700
Data Index: 4025063 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1564. Min Act: -0.1700
Data Index: 8762045 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1564. Min Act: -0.1700
Data Index: 6176917 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1722. Min Act: -0.1700
Data Index: 1416574 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1722. Min Act: -0.1700
Data Index: 2743635 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3136. Min Range: -3.3136
Max Act: 3.1407. Min Act: -0.1700
Data Index: 6811116 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19