Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0354. Min Range: -5.0354
Max Act: 5.0354. Min Act: -0.1700
Data Index: 6881022 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9729. Min Act: -0.1700
Data Index: 5689497 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0354. Min Range: -5.0354
Max Act: 5.0042. Min Act: -0.1700
Data Index: 2352677 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9729. Min Act: -0.1700
Data Index: 350901 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9417. Min Act: -0.1700
Data Index: 5689498 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9417. Min Act: -0.1700
Data Index: 7826322 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4616237 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9417. Min Act: -0.1700
Data Index: 8342772 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9104. Min Act: -0.1700
Data Index: 5689501 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4616240 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4201445 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9104. Min Act: -0.1700
Data Index: 2878062 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4657921 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4616235 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.8479. Min Act: -0.1700
Data Index: 3189303 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.8792. Min Act: -0.1700
Data Index: 4616238 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.8792. Min Act: -0.1700
Data Index: 4515990 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.8792. Min Act: -0.1700
Data Index: 4616236 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.8792. Min Act: -0.1700
Data Index: 5689500 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0354. Min Range: -5.0354
Max Act: 4.8792. Min Act: -0.1700
Data Index: 884352 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19