Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1488 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.4557. Min Act: -0.1700
Data Index: 942978 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.2994. Min Act: -0.1700
Data Index: 18697 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.2682. Min Act: -0.1700
Data Index: 1927672 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.2369. Min Act: -0.1700
Data Index: 18698 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.2682. Min Act: -0.1700
Data Index: 8633993 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.2369. Min Act: -0.1700
Data Index: 5419069 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1744. Min Act: -0.1700
Data Index: 3334521 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1744. Min Act: -0.1700
Data Index: 4589061 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1744. Min Act: -0.1700
Data Index: 421884 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1431. Min Act: -0.1700
Data Index: 139409 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1431. Min Act: -0.1700
Data Index: 4801493 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1431. Min Act: -0.1700
Data Index: 7457 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1431. Min Act: -0.1700
Data Index: 4707714 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1431. Min Act: -0.1700
Data Index: 793106 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1431. Min Act: -0.1700
Data Index: 1696786 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1119. Min Act: -0.1700
Data Index: 2060838 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1431. Min Act: -0.1700
Data Index: 3092386 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1119. Min Act: -0.1700
Data Index: 7732148 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1119. Min Act: -0.1700
Data Index: 619193 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4557. Min Range: -4.4557
Max Act: 4.1119. Min Act: -0.1700
Data Index: 8022621 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19