Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.3228. Min Act: -0.1700
Data Index: 8553203 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.1040. Min Act: -0.1700
Data Index: 3477492 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0415. Min Act: -0.1700
Data Index: 2004846 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3228. Min Range: -6.3228
Max Act: 6.0728. Min Act: -0.1700
Data Index: 1800958 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9478. Min Act: -0.1700
Data Index: 484376 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9790. Min Act: -0.1700
Data Index: 8660763 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9790. Min Act: -0.1700
Data Index: 7461804 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9165. Min Act: -0.1700
Data Index: 2595977 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9165. Min Act: -0.1700
Data Index: 3940349 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.9165. Min Act: -0.1700
Data Index: 5653365 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.8228. Min Act: -0.1700
Data Index: 4191520 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.8853. Min Act: -0.1700
Data Index: 1057904 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.7915. Min Act: -0.1700
Data Index: 2855124 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.8228. Min Act: -0.1700
Data Index: 6808621 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.8228. Min Act: -0.1700
Data Index: 3168825 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.7915. Min Act: -0.1700
Data Index: 7761812 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.7915. Min Act: -0.1700
Data Index: 6057710 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.7603. Min Act: -0.1700
Data Index: 5946587 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.7603. Min Act: -0.1700
Data Index: 2315763 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3228. Min Range: -6.3228
Max Act: 5.7290. Min Act: -0.1700
Data Index: 8569100 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19