Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4786 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.9423. Min Act: -0.1700
Data Index: 6811960 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.9423. Min Act: -0.1700
Data Index: 1432332 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8798. Min Act: -0.1700
Data Index: 2731101 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8798. Min Act: -0.1700
Data Index: 5118057 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 8369922 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 2675144 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8173. Min Act: -0.1700
Data Index: 2542061 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8173. Min Act: -0.1700
Data Index: 8455026 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8173. Min Act: -0.1700
Data Index: 6193360 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8173. Min Act: -0.1700
Data Index: 4247941 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 2420609 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 4384111 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 2831737 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 2925407 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 6981135 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7548. Min Act: -0.1700
Data Index: 4396810 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.8173. Min Act: -0.1700
Data Index: 7903033 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 1672699 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7861. Min Act: -0.1700
Data Index: 4448716 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9423. Min Range: -4.9423
Max Act: 4.7548. Min Act: -0.1700
Data Index: 3418560 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19