Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 676 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2017. Min Range: -8.2017
Max Act: 8.2017. Min Act: -0.1700
Data Index: 983567 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2017. Min Range: -8.2017
Max Act: 8.0767. Min Act: -0.1700
Data Index: 8365729 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2017. Min Range: -8.2017
Max Act: 8.0142. Min Act: -0.1700
Data Index: 117017 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.9517. Min Act: -0.1700
Data Index: 5228209 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.9517. Min Act: -0.1700
Data Index: 6385083 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.9517. Min Act: -0.1700
Data Index: 1940343 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.8892. Min Act: -0.1700
Data Index: 4919803 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.8892. Min Act: -0.1700
Data Index: 7858560 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.8267. Min Act: -0.1700
Data Index: 3992228 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7642. Min Act: -0.1700
Data Index: 2793429 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.8267. Min Act: -0.1700
Data Index: 1417622 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7642. Min Act: -0.1700
Data Index: 7669897 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7642. Min Act: -0.1700
Data Index: 994195 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7017. Min Act: -0.1700
Data Index: 3791479 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7642. Min Act: -0.1700
Data Index: 135377 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7017. Min Act: -0.1700
Data Index: 5512073 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7017. Min Act: -0.1700
Data Index: 8169270 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.7017. Min Act: -0.1700
Data Index: 4279831 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.6392. Min Act: -0.1700
Data Index: 4451438 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2017. Min Range: -8.2017
Max Act: 7.6392. Min Act: -0.1700
Data Index: 4473054 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19