Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 167 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2505. Min Range: -7.2505
Max Act: 7.2505. Min Act: -0.1700
Data Index: 2892204 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2505. Min Range: -7.2505
Max Act: 7.1567. Min Act: -0.1700
Data Index: 7454192 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2505. Min Range: -7.2505
Max Act: 7.0942. Min Act: -0.1700
Data Index: 8490718 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2505. Min Range: -7.2505
Max Act: 7.0005. Min Act: -0.1700
Data Index: 4374825 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.9692. Min Act: -0.1700
Data Index: 8050385 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.9692. Min Act: -0.1700
Data Index: 2927947 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.9692. Min Act: -0.1700
Data Index: 150375 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.9067. Min Act: -0.1700
Data Index: 4399675 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.8755. Min Act: -0.1700
Data Index: 7906955 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.8442. Min Act: -0.1700
Data Index: 6805684 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.8130. Min Act: -0.1700
Data Index: 1805345 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.7817. Min Act: -0.1700
Data Index: 6268421 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.7505. Min Act: -0.1700
Data Index: 5819904 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.7192. Min Act: -0.1700
Data Index: 2537937 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.7192. Min Act: -0.1700
Data Index: 4773289 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.6880. Min Act: -0.1700
Data Index: 8359374 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.7192. Min Act: -0.1700
Data Index: 6078695 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.7192. Min Act: -0.1700
Data Index: 1823686 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.6567. Min Act: -0.1700
Data Index: 8305662 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2505. Min Range: -7.2505
Max Act: 6.6880. Min Act: -0.1700
Data Index: 8321973 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19