Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6328 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.7348. Min Act: -0.1700
Data Index: 6876605 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.7348. Min Act: -0.1700
Data Index: 1477830 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.6723. Min Act: -0.1700
Data Index: 798873 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.6410. Min Act: -0.1700
Data Index: 4546600 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.6098. Min Act: -0.1700
Data Index: 7336043 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.5785. Min Act: -0.1700
Data Index: 8404912 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 1680967 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4535. Min Act: -0.1700
Data Index: 4395313 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 6962076 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4535. Min Act: -0.1700
Data Index: 8342227 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4848. Min Act: -0.1700
Data Index: 6694147 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4535. Min Act: -0.1700
Data Index: 8206069 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4535. Min Act: -0.1700
Data Index: 6457146 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 4514202 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 4229641 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 5007978 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3910. Min Act: -0.1700
Data Index: 4134395 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 3916870 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3910. Min Act: -0.1700
Data Index: 1611894 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3910. Min Act: -0.1700
Data Index: 3541950 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19