Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.7811. Min Act: -0.1700
Data Index: 6923169 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.6561. Min Act: -0.1700
Data Index: 5786754 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5936. Min Act: -0.1700
Data Index: 3396443 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5936. Min Act: -0.1700
Data Index: 5786752 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5624. Min Act: -0.1700
Data Index: 6955381 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5624. Min Act: -0.1700
Data Index: 5863376 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5624. Min Act: -0.1700
Data Index: 5878757 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5624. Min Act: -0.1700
Data Index: 5786753 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5311. Min Act: -0.1700
Data Index: 4531943 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5311. Min Act: -0.1700
Data Index: 92404 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5311. Min Act: -0.1700
Data Index: 5386586 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.5311. Min Act: -0.1700
Data Index: 4775975 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4999. Min Act: -0.1700
Data Index: 1316712 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4999. Min Act: -0.1700
Data Index: 4579065 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4686. Min Act: -0.1700
Data Index: 2004065 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4686. Min Act: -0.1700
Data Index: 155116 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4686. Min Act: -0.1700
Data Index: 4996423 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4686. Min Act: -0.1700
Data Index: 1794907 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4686. Min Act: -0.1700
Data Index: 637184 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7811. Min Range: -5.7811
Max Act: 5.4686. Min Act: -0.1700
Data Index: 5234102 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19