Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 639 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5730. Min Range: -5.5730
Max Act: 5.5730. Min Act: -0.1700
Data Index: 3465045 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5730. Min Range: -5.5730
Max Act: 5.1980. Min Act: -0.1700
Data Index: 2224769 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5730. Min Range: -5.5730
Max Act: 5.1667. Min Act: -0.1700
Data Index: 4265655 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5730. Min Range: -5.5730
Max Act: 5.1042. Min Act: -0.1700
Data Index: 6135216 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5730. Min Range: -5.5730
Max Act: 5.0417. Min Act: -0.1700
Data Index: 3144456 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.9792. Min Act: -0.1700
Data Index: 1058741 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.9480. Min Act: -0.1700
Data Index: 390470 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.9167. Min Act: -0.1700
Data Index: 3846867 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.9480. Min Act: -0.1700
Data Index: 7680173 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.8855. Min Act: -0.1700
Data Index: 4295196 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.7917. Min Act: -0.1700
Data Index: 2200463 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.7605. Min Act: -0.1700
Data Index: 3612146 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.7292. Min Act: -0.1700
Data Index: 6020440 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.7292. Min Act: -0.1700
Data Index: 801138 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.6980. Min Act: -0.1700
Data Index: 3846866 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.7292. Min Act: -0.1700
Data Index: 8637779 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.6667. Min Act: -0.1700
Data Index: 3164391 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.6980. Min Act: -0.1700
Data Index: 416047 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.6980. Min Act: -0.1700
Data Index: 3465047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5730. Min Range: -5.5730
Max Act: 4.6667. Min Act: -0.1700
Data Index: 2784434 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19