Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5638 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.9880. Min Act: -0.1700
Data Index: 8409800 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.7692. Min Act: -0.1700
Data Index: 37808 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.7066. Min Act: -0.1700
Data Index: 935435 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.6127. Min Act: -0.1700
Data Index: 5127614 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5814. Min Act: -0.1700
Data Index: 5272585 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5658. Min Act: -0.1700
Data Index: 8617248 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5344. Min Act: -0.1700
Data Index: 863375 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5344. Min Act: -0.1700
Data Index: 3657086 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5188. Min Act: -0.1700
Data Index: 2536752 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5344. Min Act: -0.1700
Data Index: 224626 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5188. Min Act: -0.1700
Data Index: 8294105 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5344. Min Act: -0.1700
Data Index: 6222150 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5031. Min Act: -0.1700
Data Index: 8157327 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.5188. Min Act: -0.1700
Data Index: 6352416 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.4875. Min Act: -0.1700
Data Index: 5695563 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.4875. Min Act: -0.1700
Data Index: 8676456 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.4875. Min Act: -0.1700
Data Index: 8832251 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.4718. Min Act: -0.1700
Data Index: 4807122 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.4561. Min Act: -0.1700
Data Index: 4595078 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9880. Min Range: -3.9880
Max Act: 3.4561. Min Act: -0.1700
Data Index: 6300887 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19