Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 865 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.9536. Min Act: -0.1700
Data Index: 3432613 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.8286. Min Act: -0.1700
Data Index: 102839 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.7036. Min Act: -0.1700
Data Index: 1419964 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.6411. Min Act: -0.1700
Data Index: 6004604 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.6099. Min Act: -0.1700
Data Index: 2476094 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.5786. Min Act: -0.1700
Data Index: 8148050 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.5474. Min Act: -0.1700
Data Index: 7513154 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.5786. Min Act: -0.1700
Data Index: 6209583 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.4536. Min Act: -0.1700
Data Index: 4973583 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.4224. Min Act: -0.1700
Data Index: 8475622 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.4224. Min Act: -0.1700
Data Index: 1482182 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.4536. Min Act: -0.1700
Data Index: 184574 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.4224. Min Act: -0.1700
Data Index: 6494301 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.3911. Min Act: -0.1700
Data Index: 2794016 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.3911. Min Act: -0.1700
Data Index: 1624342 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.3911. Min Act: -0.1700
Data Index: 3177934 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.3599. Min Act: -0.1700
Data Index: 4746847 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.3286. Min Act: -0.1700
Data Index: 8337352 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.3286. Min Act: -0.1700
Data Index: 6375904 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9536. Min Range: -7.9536
Max Act: 7.2974. Min Act: -0.1700
Data Index: 357100 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19