Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 978 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.7354. Min Act: -0.1700
Data Index: 7195858 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.7042. Min Act: -0.1700
Data Index: 7471851 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.6729. Min Act: -0.1700
Data Index: 7878052 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.6729. Min Act: -0.1700
Data Index: 6808871 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.5479. Min Act: -0.1700
Data Index: 2237428 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.5479. Min Act: -0.1700
Data Index: 2075003 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.5792. Min Act: -0.1700
Data Index: 5116743 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.4542. Min Act: -0.1700
Data Index: 6777839 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.4542. Min Act: -0.1700
Data Index: 2333737 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.4542. Min Act: -0.1700
Data Index: 4215177 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.4542. Min Act: -0.1700
Data Index: 5658376 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.4229. Min Act: -0.1700
Data Index: 220535 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.4229. Min Act: -0.1700
Data Index: 5647646 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.3917. Min Act: -0.1700
Data Index: 7587987 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.3917. Min Act: -0.1700
Data Index: 2447714 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.3917. Min Act: -0.1700
Data Index: 5642125 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.3604. Min Act: -0.1700
Data Index: 4392804 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.3292. Min Act: -0.1700
Data Index: 34069 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.2979. Min Act: -0.1700
Data Index: 6620788 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7354. Min Range: -6.7354
Max Act: 6.3292. Min Act: -0.1700
Data Index: 6708879 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19