Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.3124. Min Act: -0.1700
Data Index: 1559441 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2967. Min Act: -0.1700
Data Index: 4242055 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2967. Min Act: -0.1700
Data Index: 8173093 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2810. Min Act: -0.1700
Data Index: 8641598 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2496. Min Act: -0.1700
Data Index: 4860771 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2496. Min Act: -0.1700
Data Index: 4114236 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2496. Min Act: -0.1700
Data Index: 8461747 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2339. Min Act: -0.1700
Data Index: 8450702 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2496. Min Act: -0.1700
Data Index: 1457816 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2339. Min Act: -0.1700
Data Index: 521133 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2025. Min Act: -0.1700
Data Index: 2173101 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2339. Min Act: -0.1700
Data Index: 1095534 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2182. Min Act: -0.1700
Data Index: 8526045 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.1867. Min Act: -0.1700
Data Index: 5558729 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.1710. Min Act: -0.1700
Data Index: 8190722 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2025. Min Act: -0.1700
Data Index: 1001658 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.2025. Min Act: -0.1700
Data Index: 43984 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.1710. Min Act: -0.1700
Data Index: 3525261 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.1867. Min Act: -0.1700
Data Index: 7030024 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3124. Min Range: -3.3124
Max Act: 3.1867. Min Act: -0.1700
Data Index: 753792 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19