Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4524 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.5513. Min Act: -0.1700
Data Index: 4231133 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.5513. Min Act: -0.1700
Data Index: 3082133 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.5513. Min Act: -0.1700
Data Index: 2585420 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.5200. Min Act: -0.1700
Data Index: 5435264 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.5200. Min Act: -0.1700
Data Index: 8716790 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4887. Min Act: -0.1700
Data Index: 6289873 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4887. Min Act: -0.1700
Data Index: 412526 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 458242 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 4793896 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 4633046 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 7285698 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 4502130 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 8573343 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 4128334 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4887. Min Act: -0.1700
Data Index: 7444891 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4573. Min Act: -0.1700
Data Index: 2060140 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4260. Min Act: -0.1700
Data Index: 1384323 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4260. Min Act: -0.1700
Data Index: 2776053 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4260. Min Act: -0.1700
Data Index: 6009847 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5513. Min Range: -3.5513
Max Act: 3.4260. Min Act: -0.1700
Data Index: 6112161 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19