Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4262 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.7865. Min Act: -0.1700
Data Index: 6319818 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.6927. Min Act: -0.1700
Data Index: 2933932 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.6770. Min Act: -0.1700
Data Index: 7363276 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.6770. Min Act: -0.1700
Data Index: 1414274 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5988. Min Act: -0.1700
Data Index: 5840596 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5675. Min Act: -0.1700
Data Index: 4482961 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5675. Min Act: -0.1700
Data Index: 6842731 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5518. Min Act: -0.1700
Data Index: 6248066 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5205. Min Act: -0.1700
Data Index: 4433559 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5205. Min Act: -0.1700
Data Index: 8650571 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5049. Min Act: -0.1700
Data Index: 1077961 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4735. Min Act: -0.1700
Data Index: 7585560 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.5049. Min Act: -0.1700
Data Index: 8135941 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4422. Min Act: -0.1700
Data Index: 6060463 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4735. Min Act: -0.1700
Data Index: 3504908 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4265. Min Act: -0.1700
Data Index: 2464687 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4422. Min Act: -0.1700
Data Index: 4825715 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4265. Min Act: -0.1700
Data Index: 4024156 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4265. Min Act: -0.1700
Data Index: 4549492 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7865. Min Range: -3.7865
Max Act: 3.4265. Min Act: -0.1700
Data Index: 8000472 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19