Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.7356. Min Act: -0.1700
Data Index: 8412468 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.7356. Min Act: -0.1700
Data Index: 1280211 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6418. Min Act: -0.1700
Data Index: 7217032 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6418. Min Act: -0.1700
Data Index: 4084697 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6106. Min Act: -0.1700
Data Index: 4701361 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6418. Min Act: -0.1700
Data Index: 3931918 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6106. Min Act: -0.1700
Data Index: 1978866 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.5793. Min Act: -0.1700
Data Index: 3248745 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6106. Min Act: -0.1700
Data Index: 1252504 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6106. Min Act: -0.1700
Data Index: 8536599 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.5793. Min Act: -0.1700
Data Index: 7495156 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.6106. Min Act: -0.1700
Data Index: 1600055 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.5793. Min Act: -0.1700
Data Index: 4396849 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.5481. Min Act: -0.1700
Data Index: 3472582 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.5481. Min Act: -0.1700
Data Index: 4434359 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.5168. Min Act: -0.1700
Data Index: 8360954 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.4856. Min Act: -0.1700
Data Index: 8395339 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.4856. Min Act: -0.1700
Data Index: 8405176 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.5168. Min Act: -0.1700
Data Index: 4123757 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7356. Min Range: -6.7356
Max Act: 6.4856. Min Act: -0.1700
Data Index: 7420195 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19