Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1769 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.6148. Min Act: -0.1700
Data Index: 8285799 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.6148. Min Act: -0.1700
Data Index: 302245 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.5836. Min Act: -0.1700
Data Index: 263783 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.5836. Min Act: -0.1700
Data Index: 4917564 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.5836. Min Act: -0.1700
Data Index: 318936 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.5211. Min Act: -0.1700
Data Index: 8793572 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.5211. Min Act: -0.1700
Data Index: 7557908 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.5523. Min Act: -0.1700
Data Index: 8793574 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.5523. Min Act: -0.1700
Data Index: 5566592 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4898. Min Act: -0.1700
Data Index: 531771 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4898. Min Act: -0.1700
Data Index: 8793573 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4898. Min Act: -0.1700
Data Index: 3154478 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4586. Min Act: -0.1700
Data Index: 1457817 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4273. Min Act: -0.1700
Data Index: 2651935 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4273. Min Act: -0.1700
Data Index: 6150806 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4273. Min Act: -0.1700
Data Index: 1526141 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.4273. Min Act: -0.1700
Data Index: 1577840 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.3961. Min Act: -0.1700
Data Index: 8680122 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.3961. Min Act: -0.1700
Data Index: 4995240 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6148. Min Range: -5.6148
Max Act: 5.3961. Min Act: -0.1700
Data Index: 4995239 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19