Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4009 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.6923. Min Act: -0.1700
Data Index: 6280512 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.5986. Min Act: -0.1700
Data Index: 7109300 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.4736. Min Act: -0.1700
Data Index: 8248378 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.4111. Min Act: -0.1700
Data Index: 6193164 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.4111. Min Act: -0.1700
Data Index: 5744699 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.3798. Min Act: -0.1700
Data Index: 3080246 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.3486. Min Act: -0.1700
Data Index: 3330258 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.3173. Min Act: -0.1700
Data Index: 7961961 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.3173. Min Act: -0.1700
Data Index: 5622046 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2861. Min Act: -0.1700
Data Index: 4154357 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2548. Min Act: -0.1700
Data Index: 4402214 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2548. Min Act: -0.1700
Data Index: 8471463 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2548. Min Act: -0.1700
Data Index: 5177977 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2548. Min Act: -0.1700
Data Index: 3626233 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2236. Min Act: -0.1700
Data Index: 7457996 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2236. Min Act: -0.1700
Data Index: 2888643 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.2236. Min Act: -0.1700
Data Index: 7064284 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.1923. Min Act: -0.1700
Data Index: 7817565 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.1923. Min Act: -0.1700
Data Index: 605505 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6923. Min Range: -7.6923
Max Act: 7.1923. Min Act: -0.1700
Data Index: 1752743 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19