Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.5923. Min Act: -0.1700
Data Index: 89259 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.2173. Min Act: -0.1700
Data Index: 4924859 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.2173. Min Act: -0.1700
Data Index: 484002 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.2173. Min Act: -0.1700
Data Index: 401646 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.2173. Min Act: -0.1700
Data Index: 6914177 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.0923. Min Act: -0.1700
Data Index: 1185669 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.0923. Min Act: -0.1700
Data Index: 4875560 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.0923. Min Act: -0.1700
Data Index: 371121 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.0298. Min Act: -0.1700
Data Index: 1238209 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.0298. Min Act: -0.1700
Data Index: 5548098 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9673. Min Act: -0.1700
Data Index: 5063987 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.0298. Min Act: -0.1700
Data Index: 7304301 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9673. Min Act: -0.1700
Data Index: 304499 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9673. Min Act: -0.1700
Data Index: 2785071 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5923. Min Range: -8.5923
Max Act: 8.0298. Min Act: -0.1700
Data Index: 892911 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9673. Min Act: -0.1700
Data Index: 8831467 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9048. Min Act: -0.1700
Data Index: 5280489 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9048. Min Act: -0.1700
Data Index: 2909391 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9048. Min Act: -0.1700
Data Index: 4479121 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5923. Min Range: -8.5923
Max Act: 7.9048. Min Act: -0.1700
Data Index: 5326031 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19