Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.9850. Min Act: -0.1700
Data Index: 1133635 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.9225. Min Act: -0.1700
Data Index: 5510006 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.7037. Min Act: -0.1700
Data Index: 8163286 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.6725. Min Act: -0.1700
Data Index: 509907 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.6412. Min Act: -0.1700
Data Index: 5510005 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.6412. Min Act: -0.1700
Data Index: 382544 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.6100. Min Act: -0.1700
Data Index: 1638343 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.5787. Min Act: -0.1700
Data Index: 3786503 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.5787. Min Act: -0.1700
Data Index: 1022673 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.5787. Min Act: -0.1700
Data Index: 1727960 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.4850. Min Act: -0.1700
Data Index: 7946753 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.4850. Min Act: -0.1700
Data Index: 727120 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.4537. Min Act: -0.1700
Data Index: 4332905 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.4225. Min Act: -0.1700
Data Index: 4636958 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.4225. Min Act: -0.1700
Data Index: 1996897 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.4225. Min Act: -0.1700
Data Index: 2875214 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.3912. Min Act: -0.1700
Data Index: 1886743 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.3912. Min Act: -0.1700
Data Index: 3459951 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.3600. Min Act: -0.1700
Data Index: 2383433 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9850. Min Range: -5.9850
Max Act: 5.3287. Min Act: -0.1700
Data Index: 2229719 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19