Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.7030. Min Act: -0.1700
Data Index: 899473 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.6405. Min Act: -0.1700
Data Index: 7080380 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.5780. Min Act: -0.1700
Data Index: 8580018 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.4530. Min Act: -0.1700
Data Index: 4541929 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.3905. Min Act: -0.1700
Data Index: 244004 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.3905. Min Act: -0.1700
Data Index: 5960306 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.3905. Min Act: -0.1700
Data Index: 5226562 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.3905. Min Act: -0.1700
Data Index: 3141219 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.3280. Min Act: -0.1700
Data Index: 30860 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.3280. Min Act: -0.1700
Data Index: 5435424 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.2655. Min Act: -0.1700
Data Index: 3059558 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.2030. Min Act: -0.1700
Data Index: 7159298 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.2030. Min Act: -0.1700
Data Index: 2382138 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.1405. Min Act: -0.1700
Data Index: 4635898 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.1405. Min Act: -0.1700
Data Index: 1036363 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.1405. Min Act: -0.1700
Data Index: 6169053 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.1405. Min Act: -0.1700
Data Index: 3846496 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.1405. Min Act: -0.1700
Data Index: 6415717 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.2030. Min Act: -0.1700
Data Index: 2867300 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7030. Min Range: -10.7030
Max Act: 10.0780. Min Act: -0.1700
Data Index: 2570838 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19