Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.5408. Min Act: -0.1700
Data Index: 2996707 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.4783. Min Act: -0.1700
Data Index: 4966344 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.4783. Min Act: -0.1700
Data Index: 5790987 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.4158. Min Act: -0.1700
Data Index: 1480030 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.4783. Min Act: -0.1700
Data Index: 6792259 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.4783. Min Act: -0.1700
Data Index: 7583769 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.4158. Min Act: -0.1700
Data Index: 6533154 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.4158. Min Act: -0.1700
Data Index: 768816 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.3533. Min Act: -0.1700
Data Index: 1480029 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.3533. Min Act: -0.1700
Data Index: 1529589 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2908. Min Act: -0.1700
Data Index: 6835176 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2908. Min Act: -0.1700
Data Index: 1201751 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2908. Min Act: -0.1700
Data Index: 6353094 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2283. Min Act: -0.1700
Data Index: 8473581 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2283. Min Act: -0.1700
Data Index: 2489327 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2283. Min Act: -0.1700
Data Index: 2341953 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2283. Min Act: -0.1700
Data Index: 1808809 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.2283. Min Act: -0.1700
Data Index: 5024454 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.1658. Min Act: -0.1700
Data Index: 784516 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5408. Min Range: -8.5408
Max Act: 8.1658. Min Act: -0.1700
Data Index: 4060060 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19