Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 480 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0918. Min Range: -9.0918
Max Act: 9.0918. Min Act: -0.1700
Data Index: 2103060 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.7793. Min Act: -0.1700
Data Index: 4299054 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.5918. Min Act: -0.1700
Data Index: 4299063 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.5918. Min Act: -0.1700
Data Index: 7958069 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.4668. Min Act: -0.1700
Data Index: 2546987 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.4668. Min Act: -0.1700
Data Index: 6254550 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.4668. Min Act: -0.1700
Data Index: 7149371 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.3418. Min Act: -0.1700
Data Index: 3044647 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.3418. Min Act: -0.1700
Data Index: 2250185 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.3418. Min Act: -0.1700
Data Index: 8460055 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.3418. Min Act: -0.1700
Data Index: 8124198 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.2168. Min Act: -0.1700
Data Index: 3101724 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.2793. Min Act: -0.1700
Data Index: 6714025 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.2793. Min Act: -0.1700
Data Index: 6136026 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.2168. Min Act: -0.1700
Data Index: 783954 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.2168. Min Act: -0.1700
Data Index: 19349 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.2168. Min Act: -0.1700
Data Index: 1916610 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.2168. Min Act: -0.1700
Data Index: 3798515 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.1543. Min Act: -0.1700
Data Index: 2659851 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0918. Min Range: -9.0918
Max Act: 8.1543. Min Act: -0.1700
Data Index: 777757 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19