Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4020. Min Range: -7.4020
Max Act: 7.4020. Min Act: -0.1700
Data Index: 3142975 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.8707. Min Act: -0.1700
Data Index: 8657765 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.8395. Min Act: -0.1700
Data Index: 7259580 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.6832. Min Act: -0.1700
Data Index: 4856574 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.6832. Min Act: -0.1700
Data Index: 4809090 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.6520. Min Act: -0.1700
Data Index: 5733312 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.6520. Min Act: -0.1700
Data Index: 3485719 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.6207. Min Act: -0.1700
Data Index: 2543883 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.5895. Min Act: -0.1700
Data Index: 5012983 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.5895. Min Act: -0.1700
Data Index: 5967351 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4645. Min Act: -0.1700
Data Index: 7118359 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4645. Min Act: -0.1700
Data Index: 2280862 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4645. Min Act: -0.1700
Data Index: 3638652 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4957. Min Act: -0.1700
Data Index: 1849161 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4332. Min Act: -0.1700
Data Index: 4599788 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4332. Min Act: -0.1700
Data Index: 476969 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4332. Min Act: -0.1700
Data Index: 1492489 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4332. Min Act: -0.1700
Data Index: 4046725 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 3716191 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4020. Min Range: -7.4020
Max Act: 6.3707. Min Act: -0.1700
Data Index: 2288244 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19