Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.8582. Min Act: -0.1700
Data Index: 2976899 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.8270. Min Act: -0.1700
Data Index: 6149835 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.7957. Min Act: -0.1700
Data Index: 8561481 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.7645. Min Act: -0.1700
Data Index: 8074552 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.7332. Min Act: -0.1700
Data Index: 6384024 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.7332. Min Act: -0.1700
Data Index: 6420113 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.7332. Min Act: -0.1700
Data Index: 7498418 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.7332. Min Act: -0.1700
Data Index: 4100196 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6707. Min Act: -0.1700
Data Index: 8166613 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6707. Min Act: -0.1700
Data Index: 2225903 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6707. Min Act: -0.1700
Data Index: 8762529 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6707. Min Act: -0.1700
Data Index: 2797160 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6707. Min Act: -0.1700
Data Index: 5773255 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6707. Min Act: -0.1700
Data Index: 3321973 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6707. Min Act: -0.1700
Data Index: 4198346 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7684426 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7927059 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6395. Min Act: -0.1700
Data Index: 1979236 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6395. Min Act: -0.1700
Data Index: 8479449 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8582. Min Range: -5.8582
Max Act: 5.6082. Min Act: -0.1699
Data Index: 5096996 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19