Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.8801. Min Act: -0.1666
Data Index: 3202555 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.8201. Min Act: -0.1700
Data Index: 8785522 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7857. Min Act: -0.1700
Data Index: 906347 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7857. Min Act: -0.1699
Data Index: 6482648 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7771. Min Act: -0.1700
Data Index: 3971785 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7771. Min Act: -0.1700
Data Index: 1662794 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7598. Min Act: -0.1648
Data Index: 218046 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7598. Min Act: -0.1700
Data Index: 3694499 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7598. Min Act: -0.1697
Data Index: 3679808 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7598. Min Act: -0.1697
Data Index: 5928697 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7426. Min Act: -0.1697
Data Index: 5606538 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7426. Min Act: -0.1700
Data Index: 1173374 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7512. Min Act: -0.1695
Data Index: 7866580 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7339. Min Act: -0.1696
Data Index: 7074081 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7253. Min Act: -0.1700
Data Index: 7490947 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7426. Min Act: -0.1700
Data Index: 2671220 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7253. Min Act: -0.1700
Data Index: 705827 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7253. Min Act: -0.1700
Data Index: 7866681 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7166. Min Act: -0.1700
Data Index: 2647967 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8801. Min Range: -1.8801
Max Act: 1.7166. Min Act: -0.1700
Data Index: 8552915 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19