Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.7954. Min Act: -0.1700
Data Index: 6635146 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.7954. Min Act: -0.1700
Data Index: 2510018 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.7017. Min Act: -0.1700
Data Index: 2831435 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.5454. Min Act: -0.1700
Data Index: 4119551 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.5142. Min Act: -0.1700
Data Index: 1678480 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.4517. Min Act: -0.1700
Data Index: 3425934 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.3579. Min Act: -0.1700
Data Index: 5397034 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.3892. Min Act: -0.1700
Data Index: 5302191 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.3579. Min Act: -0.1700
Data Index: 2135858 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.2954. Min Act: -0.1700
Data Index: 3836218 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.2954. Min Act: -0.1700
Data Index: 2810963 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.2954. Min Act: -0.1700
Data Index: 4058552 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.2642. Min Act: -0.1700
Data Index: 4349107 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.1704. Min Act: -0.1700
Data Index: 2243589 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.1392. Min Act: -0.1700
Data Index: 6421718 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.1079. Min Act: -0.1700
Data Index: 853012 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.1392. Min Act: -0.1700
Data Index: 246159 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.1079. Min Act: -0.1700
Data Index: 4176595 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.1079. Min Act: -0.1700
Data Index: 5235690 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7954. Min Range: -6.7954
Max Act: 6.1079. Min Act: -0.1700
Data Index: 5570596 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19