Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2519 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1226. Min Range: -6.1226
Max Act: 6.1226. Min Act: -0.1700
Data Index: 2726496 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1226. Min Range: -6.1226
Max Act: 6.0914. Min Act: -0.1700
Data Index: 5228772 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1226. Min Range: -6.1226
Max Act: 6.0289. Min Act: -0.1700
Data Index: 6819109 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1226. Min Range: -6.1226
Max Act: 6.0601. Min Act: -0.1700
Data Index: 8564705 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9976. Min Act: -0.1700
Data Index: 6350575 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9976. Min Act: -0.1699
Data Index: 1076546 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9976. Min Act: -0.1700
Data Index: 242200 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9976. Min Act: -0.1700
Data Index: 2213678 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9664. Min Act: -0.1700
Data Index: 8611725 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9351. Min Act: -0.1700
Data Index: 6061404 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9351. Min Act: -0.1700
Data Index: 6379661 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9039. Min Act: -0.1700
Data Index: 6924760 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9039. Min Act: -0.1700
Data Index: 4073539 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9351. Min Act: -0.1700
Data Index: 6338488 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9039. Min Act: -0.1700
Data Index: 1392420 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.8726. Min Act: -0.1700
Data Index: 2814491 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.8726. Min Act: -0.1700
Data Index: 4285650 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9039. Min Act: -0.1700
Data Index: 591802 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.9039. Min Act: -0.1700
Data Index: 8187541 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1226. Min Range: -6.1226
Max Act: 5.8726. Min Act: -0.1700
Data Index: 2750776 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19