Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6167 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.5291. Min Act: -0.1700
Data Index: 2697802 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.4041. Min Act: -0.1700
Data Index: 8573454 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.2478. Min Act: -0.1700
Data Index: 4653924 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.1853. Min Act: -0.1700
Data Index: 5611292 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.1541. Min Act: -0.1700
Data Index: 5615401 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.1228. Min Act: -0.1700
Data Index: 1337020 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.1228. Min Act: -0.1700
Data Index: 1337021 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.1541. Min Act: -0.1700
Data Index: 343888 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.1228. Min Act: -0.1700
Data Index: 5632710 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0916. Min Act: -0.1700
Data Index: 2310781 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0916. Min Act: -0.1700
Data Index: 4938247 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0916. Min Act: -0.1700
Data Index: 2464765 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0603. Min Act: -0.1700
Data Index: 5057240 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0916. Min Act: -0.1700
Data Index: 4145989 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0291. Min Act: -0.1700
Data Index: 2621411 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0603. Min Act: -0.1700
Data Index: 2014306 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0603. Min Act: -0.1700
Data Index: 3431504 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0291. Min Act: -0.1700
Data Index: 3220295 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0603. Min Act: -0.1700
Data Index: 6745841 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5291. Min Range: -5.5291
Max Act: 5.0603. Min Act: -0.1700
Data Index: 7109860 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19