Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4877 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1342. Min Range: -8.1342
Max Act: 8.1342. Min Act: -0.1700
Data Index: 802315 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1342. Min Range: -8.1342
Max Act: 8.0092. Min Act: -0.1700
Data Index: 7110837 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.9155. Min Act: -0.1700
Data Index: 6251603 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.7592. Min Act: -0.1700
Data Index: 8724054 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.7592. Min Act: -0.1700
Data Index: 2173173 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.6967. Min Act: -0.1700
Data Index: 6137538 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.6967. Min Act: -0.1700
Data Index: 3394858 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.6655. Min Act: -0.1700
Data Index: 8777482 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.5717. Min Act: -0.1700
Data Index: 8691387 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.5717. Min Act: -0.1700
Data Index: 1726285 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.5405. Min Act: -0.1700
Data Index: 685886 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.5092. Min Act: -0.1700
Data Index: 4006513 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.4780. Min Act: -0.1700
Data Index: 46505 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.4155. Min Act: -0.1700
Data Index: 7265870 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.4155. Min Act: -0.1700
Data Index: 7612471 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.4155. Min Act: -0.1700
Data Index: 3650055 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.3842. Min Act: -0.1700
Data Index: 673420 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.3530. Min Act: -0.1700
Data Index: 6152972 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.3842. Min Act: -0.1700
Data Index: 3411466 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1342. Min Range: -8.1342
Max Act: 7.3530. Min Act: -0.1700
Data Index: 4784763 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19