Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4111 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0022. Min Range: -5.0022
Max Act: 5.0022. Min Act: -0.1700
Data Index: 2081602 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0022. Min Range: -5.0022
Max Act: 5.0022. Min Act: -0.1700
Data Index: 6630467 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9710. Min Act: -0.1700
Data Index: 4787724 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9710. Min Act: -0.1700
Data Index: 7489290 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9397. Min Act: -0.1700
Data Index: 7672249 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9397. Min Act: -0.1700
Data Index: 7063963 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9397. Min Act: -0.1700
Data Index: 976322 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9085. Min Act: -0.1700
Data Index: 2992155 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9085. Min Act: -0.1700
Data Index: 707402 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.9397. Min Act: -0.1700
Data Index: 2982173 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.8772. Min Act: -0.1700
Data Index: 2734614 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.8460. Min Act: -0.1700
Data Index: 7150296 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.8460. Min Act: -0.1700
Data Index: 7398441 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.8147. Min Act: -0.1700
Data Index: 6321944 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.8460. Min Act: -0.1700
Data Index: 8376725 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.8147. Min Act: -0.1700
Data Index: 2134496 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.7835. Min Act: -0.1700
Data Index: 8055625 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.7835. Min Act: -0.1700
Data Index: 3328983 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.7835. Min Act: -0.1700
Data Index: 627625 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0022. Min Range: -5.0022
Max Act: 4.7835. Min Act: -0.1700
Data Index: 4663778 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19