Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4860 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.9171. Min Act: -0.1700
Data Index: 7602506 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.8859. Min Act: -0.1700
Data Index: 2744863 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.8859. Min Act: -0.1700
Data Index: 2444686 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.8546. Min Act: -0.1700
Data Index: 5248572 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.7296. Min Act: -0.1700
Data Index: 8084266 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.7609. Min Act: -0.1700
Data Index: 967430 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6984. Min Act: -0.1700
Data Index: 7098313 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6984. Min Act: -0.1700
Data Index: 2310349 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6984. Min Act: -0.1700
Data Index: 1047891 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6671. Min Act: -0.1700
Data Index: 4432106 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6359. Min Act: -0.1700
Data Index: 5423856 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6046. Min Act: -0.1700
Data Index: 2360923 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6359. Min Act: -0.1700
Data Index: 649984 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6046. Min Act: -0.1700
Data Index: 4456045 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.5734. Min Act: -0.1699
Data Index: 6291806 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.5734. Min Act: -0.1700
Data Index: 1933265 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6046. Min Act: -0.1700
Data Index: 5242954 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.6046. Min Act: -0.1700
Data Index: 5378090 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.5734. Min Act: -0.1700
Data Index: 1140667 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9171. Min Range: -6.9171
Max Act: 6.5734. Min Act: -0.1700
Data Index: 5368608 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19