Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9445. Min Act: -0.1700
Data Index: 6423565 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9287. Min Act: -0.1700
Data Index: 6388900 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9287. Min Act: -0.1700
Data Index: 5463442 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9445. Min Act: -0.1700
Data Index: 2169536 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9128. Min Act: -0.1700
Data Index: 5079599 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8970. Min Act: -0.1700
Data Index: 6539895 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9128. Min Act: -0.1700
Data Index: 2268677 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9128. Min Act: -0.1700
Data Index: 2281612 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9128. Min Act: -0.1700
Data Index: 870916 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8970. Min Act: -0.1700
Data Index: 141971 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8970. Min Act: -0.1700
Data Index: 6238991 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8811. Min Act: -0.1700
Data Index: 4421001 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8970. Min Act: -0.1700
Data Index: 2830367 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8811. Min Act: -0.1700
Data Index: 4235398 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8970. Min Act: -0.1700
Data Index: 5641468 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8811. Min Act: -0.1700
Data Index: 6762822 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8811. Min Act: -0.1700
Data Index: 538241 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 1707102 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 3718557 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 1694831 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19