Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6392 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4289. Min Range: -7.4289
Max Act: 7.4289. Min Act: -0.1700
Data Index: 2831487 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4289. Min Range: -7.4289
Max Act: 7.1789. Min Act: -0.1700
Data Index: 2699699 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4289. Min Range: -7.4289
Max Act: 7.1789. Min Act: -0.1700
Data Index: 326831 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4289. Min Range: -7.4289
Max Act: 7.1164. Min Act: -0.1700
Data Index: 7943949 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4289. Min Range: -7.4289
Max Act: 7.1164. Min Act: -0.1700
Data Index: 8612250 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4289. Min Range: -7.4289
Max Act: 7.0539. Min Act: -0.1700
Data Index: 988882 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.9289. Min Act: -0.1700
Data Index: 3095823 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.9289. Min Act: -0.1700
Data Index: 3145618 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8976. Min Act: -0.1700
Data Index: 3683372 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8976. Min Act: -0.1700
Data Index: 7963 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8664. Min Act: -0.1700
Data Index: 2242500 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8351. Min Act: -0.1700
Data Index: 7808989 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8039. Min Act: -0.1700
Data Index: 67141 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8351. Min Act: -0.1700
Data Index: 5864152 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8351. Min Act: -0.1700
Data Index: 3259850 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.8039. Min Act: -0.1700
Data Index: 7959174 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.7414. Min Act: -0.1700
Data Index: 5112698 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.7414. Min Act: -0.1700
Data Index: 1706452 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.7101. Min Act: -0.1700
Data Index: 1569679 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4289. Min Range: -7.4289
Max Act: 6.6789. Min Act: -0.1700
Data Index: 5799395 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19