Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.6308. Min Act: -0.1700
Data Index: 4957623 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.5995. Min Act: -0.1700
Data Index: 2733307 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.5682. Min Act: -0.1700
Data Index: 7477000 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.3488. Min Act: -0.1700
Data Index: 1536814 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.2075. Min Act: -0.1700
Data Index: 6942361 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.2389. Min Act: -0.1700
Data Index: 4694430 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.1918. Min Act: -0.1700
Data Index: 3047485 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.1760. Min Act: -0.1700
Data Index: 230001 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.1603. Min Act: -0.1700
Data Index: 7476997 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.1603. Min Act: -0.1700
Data Index: 2896002 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.1288. Min Act: -0.1700
Data Index: 328002 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.1288. Min Act: -0.1700
Data Index: 1673672 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.1288. Min Act: -0.1700
Data Index: 8165985 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.0815. Min Act: -0.1700
Data Index: 6749008 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.0658. Min Act: -0.1700
Data Index: 7415442 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.0815. Min Act: -0.1700
Data Index: 328003 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.0815. Min Act: -0.1700
Data Index: 6749010 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.0815. Min Act: -0.1700
Data Index: 5646917 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.0658. Min Act: -0.1700
Data Index: 327999 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6308. Min Range: -3.6308
Max Act: 3.0500. Min Act: -0.1700
Data Index: 4894512 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19