Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5345 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.4614. Min Act: -0.1700
Data Index: 8462858 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.4301. Min Act: -0.1700
Data Index: 4391905 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.3989. Min Act: -0.1700
Data Index: 4759114 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.3676. Min Act: -0.1700
Data Index: 5405048 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.2739. Min Act: -0.1700
Data Index: 6655996 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.2426. Min Act: -0.1700
Data Index: 691259 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.2739. Min Act: -0.1700
Data Index: 244767 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.2739. Min Act: -0.1700
Data Index: 2700921 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.2426. Min Act: -0.1700
Data Index: 3353995 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.2426. Min Act: -0.1700
Data Index: 235845 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.2426. Min Act: -0.1700
Data Index: 7920220 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1801. Min Act: -0.1700
Data Index: 4041159 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1801. Min Act: -0.1700
Data Index: 3816148 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1801. Min Act: -0.1700
Data Index: 5084568 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1801. Min Act: -0.1700
Data Index: 798089 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1801. Min Act: -0.1700
Data Index: 49474 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1801. Min Act: -0.1700
Data Index: 1519989 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1488. Min Act: -0.1700
Data Index: 4908443 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1488. Min Act: -0.1700
Data Index: 1632106 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4614. Min Range: -4.4614
Max Act: 4.1488. Min Act: -0.1700
Data Index: 4555940 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19