Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0467. Min Range: -7.0467
Max Act: 7.0467. Min Act: -0.1700
Data Index: 3804881 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.7030. Min Act: -0.1700
Data Index: 678426 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.5155. Min Act: -0.1700
Data Index: 1940820 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.4217. Min Act: -0.1700
Data Index: 6490967 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.3592. Min Act: -0.1700
Data Index: 5865039 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2967. Min Act: -0.1700
Data Index: 2495965 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.3280. Min Act: -0.1700
Data Index: 4854425 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2967. Min Act: -0.1700
Data Index: 6241825 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2967. Min Act: -0.1700
Data Index: 19985 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2655. Min Act: -0.1700
Data Index: 5596468 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2030. Min Act: -0.1700
Data Index: 2557535 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2342. Min Act: -0.1700
Data Index: 4820946 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2030. Min Act: -0.1700
Data Index: 1252080 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.2030. Min Act: -0.1700
Data Index: 4220078 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.1405. Min Act: -0.1700
Data Index: 7889087 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.1092. Min Act: -0.1700
Data Index: 5960950 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.1092. Min Act: -0.1700
Data Index: 1638926 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.1092. Min Act: -0.1700
Data Index: 1350944 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.1092. Min Act: -0.1700
Data Index: 3971170 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0467. Min Range: -7.0467
Max Act: 6.0780. Min Act: -0.1700
Data Index: 3820970 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19