Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2063 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.7411. Min Act: -0.1700
Data Index: 2124313 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.6473. Min Act: -0.1700
Data Index: 6743015 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.6161. Min Act: -0.1700
Data Index: 536135 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.6161. Min Act: -0.1700
Data Index: 2798466 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5848. Min Act: -0.1700
Data Index: 1492555 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5536. Min Act: -0.1700
Data Index: 5961092 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5848. Min Act: -0.1700
Data Index: 8226912 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5536. Min Act: -0.1700
Data Index: 8507479 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5223. Min Act: -0.1700
Data Index: 400155 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5223. Min Act: -0.1700
Data Index: 8704938 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5223. Min Act: -0.1700
Data Index: 5333878 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5223. Min Act: -0.1700
Data Index: 1024062 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.5223. Min Act: -0.1700
Data Index: 7320852 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 1824430 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 4875116 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 942334 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 749117 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 5423604 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4911. Min Act: -0.1700
Data Index: 4879839 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7411. Min Range: -5.7411
Max Act: 5.4598. Min Act: -0.1700
Data Index: 6833350 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19