Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2150. Min Range: -5.2150
Max Act: 5.2150. Min Act: -0.1700
Data Index: 6186698 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2150. Min Range: -5.2150
Max Act: 5.0900. Min Act: -0.1700
Data Index: 6048835 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9963. Min Act: -0.1700
Data Index: 1886544 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2150. Min Range: -5.2150
Max Act: 5.0275. Min Act: -0.1700
Data Index: 5584687 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2150. Min Range: -5.2150
Max Act: 5.0275. Min Act: -0.1700
Data Index: 4798164 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2150. Min Range: -5.2150
Max Act: 5.0275. Min Act: -0.1700
Data Index: 6772200 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2150. Min Range: -5.2150
Max Act: 5.0275. Min Act: -0.1700
Data Index: 4880645 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9650. Min Act: -0.1700
Data Index: 8447237 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9338. Min Act: -0.1700
Data Index: 3064321 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9650. Min Act: -0.1700
Data Index: 6204764 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9650. Min Act: -0.1700
Data Index: 8694453 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9650. Min Act: -0.1700
Data Index: 8447277 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9338. Min Act: -0.1700
Data Index: 6332994 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9338. Min Act: -0.1700
Data Index: 7733929 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9338. Min Act: -0.1700
Data Index: 3229265 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9025. Min Act: -0.1700
Data Index: 1696296 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9025. Min Act: -0.1700
Data Index: 1886541 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9025. Min Act: -0.1700
Data Index: 3868740 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9025. Min Act: -0.1700
Data Index: 594103 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2150. Min Range: -5.2150
Max Act: 4.9025. Min Act: -0.1700
Data Index: 2749469 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19