Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6399 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.9259. Min Act: -0.1700
Data Index: 4520277 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.8634. Min Act: -0.1700
Data Index: 6756971 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.4259. Min Act: -0.1700
Data Index: 3913642 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.3947. Min Act: -0.1700
Data Index: 7717936 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.3634. Min Act: -0.1700
Data Index: 4749132 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.3634. Min Act: -0.1700
Data Index: 8178324 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.3322. Min Act: -0.1700
Data Index: 420388 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.2384. Min Act: -0.1700
Data Index: 6445735 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.2072. Min Act: -0.1700
Data Index: 1298514 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.2072. Min Act: -0.1700
Data Index: 4377092 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.2072. Min Act: -0.1700
Data Index: 5589496 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.1759. Min Act: -0.1700
Data Index: 7269575 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.1447. Min Act: -0.1700
Data Index: 3095398 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.1134. Min Act: -0.1700
Data Index: 7283847 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.1134. Min Act: -0.1700
Data Index: 3264860 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.0509. Min Act: -0.1700
Data Index: 1800588 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.0822. Min Act: -0.1700
Data Index: 2334298 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.0509. Min Act: -0.1700
Data Index: 680105 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.0509. Min Act: -0.1700
Data Index: 1413840 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9259. Min Range: -6.9259
Max Act: 6.0509. Min Act: -0.1700
Data Index: 6434010 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19