Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 305 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1688. Min Range: -8.1688
Max Act: 8.1688. Min Act: -0.1700
Data Index: 433261 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1688. Min Range: -8.1688
Max Act: 8.1063. Min Act: -0.1700
Data Index: 1473393 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.9500. Min Act: -0.1700
Data Index: 7434201 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.9188. Min Act: -0.1700
Data Index: 2488263 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.9500. Min Act: -0.1700
Data Index: 1600710 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.8250. Min Act: -0.1700
Data Index: 6615142 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.7938. Min Act: -0.1700
Data Index: 1906756 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.7000. Min Act: -0.1700
Data Index: 4266573 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.6688. Min Act: -0.1700
Data Index: 6773381 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.6375. Min Act: -0.1700
Data Index: 7508204 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.6375. Min Act: -0.1700
Data Index: 3694602 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.6375. Min Act: -0.1700
Data Index: 8516139 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.6063. Min Act: -0.1700
Data Index: 2570571 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.6063. Min Act: -0.1700
Data Index: 5129685 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.5750. Min Act: -0.1700
Data Index: 4829495 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.5750. Min Act: -0.1700
Data Index: 2516290 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.5750. Min Act: -0.1700
Data Index: 4000427 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.5438. Min Act: -0.1700
Data Index: 8551003 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.5438. Min Act: -0.1700
Data Index: 900470 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1688. Min Range: -8.1688
Max Act: 7.5438. Min Act: -0.1700
Data Index: 6077904 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19