Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.6723. Min Act: -0.1700
Data Index: 1636049 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.6723. Min Act: -0.1700
Data Index: 4991726 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.4536. Min Act: -0.1700
Data Index: 6933941 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.4536. Min Act: -0.1700
Data Index: 3476701 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.4536. Min Act: -0.1700
Data Index: 1074276 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.3911. Min Act: -0.1700
Data Index: 1935796 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.4223. Min Act: -0.1700
Data Index: 3457671 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.3598. Min Act: -0.1700
Data Index: 6078797 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.3286. Min Act: -0.1700
Data Index: 5645974 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.3286. Min Act: -0.1700
Data Index: 3249557 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.3286. Min Act: -0.1700
Data Index: 991318 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.3286. Min Act: -0.1700
Data Index: 3899489 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2973. Min Act: -0.1700
Data Index: 5737765 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2973. Min Act: -0.1700
Data Index: 1552830 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2661. Min Act: -0.1700
Data Index: 5278842 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2661. Min Act: -0.1700
Data Index: 891038 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2661. Min Act: -0.1700
Data Index: 1267626 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2661. Min Act: -0.1700
Data Index: 1004622 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2661. Min Act: -0.1700
Data Index: 4936728 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6723. Min Range: -5.6723
Max Act: 5.2661. Min Act: -0.1700
Data Index: 5799355 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19