Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.3679. Min Act: -0.1700
Data Index: 491511 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.3366. Min Act: -0.1700
Data Index: 2996408 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.3366. Min Act: -0.1700
Data Index: 7842866 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.3054. Min Act: -0.1700
Data Index: 3401995 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.2429. Min Act: -0.1700
Data Index: 3035487 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.2116. Min Act: -0.1700
Data Index: 7684019 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.2116. Min Act: -0.1700
Data Index: 843402 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.1804. Min Act: -0.1700
Data Index: 383420 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.1179. Min Act: -0.1700
Data Index: 4966377 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0866. Min Act: -0.1700
Data Index: 838473 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0866. Min Act: -0.1700
Data Index: 3020432 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0554. Min Act: -0.1700
Data Index: 348181 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0554. Min Act: -0.1700
Data Index: 2529159 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0241. Min Act: -0.1700
Data Index: 3147940 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0241. Min Act: -0.1700
Data Index: 6230993 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0554. Min Act: -0.1700
Data Index: 1808774 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0241. Min Act: -0.1700
Data Index: 1272153 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9929. Min Act: -0.1700
Data Index: 5524099 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9616. Min Act: -0.1700
Data Index: 896285 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9616. Min Act: -0.1700
Data Index: 3242619 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19