Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0383. Min Range: -8.0383
Max Act: 8.0383. Min Act: -0.1700
Data Index: 8671027 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.9758. Min Act: -0.1700
Data Index: 741194 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.8195. Min Act: -0.1700
Data Index: 5217047 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.7258. Min Act: -0.1700
Data Index: 8706424 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.6320. Min Act: -0.1700
Data Index: 8448545 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.6320. Min Act: -0.1700
Data Index: 1676699 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.6320. Min Act: -0.1700
Data Index: 5398009 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.6320. Min Act: -0.1700
Data Index: 7856032 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.5383. Min Act: -0.1700
Data Index: 6606317 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.5695. Min Act: -0.1700
Data Index: 4443909 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.5695. Min Act: -0.1700
Data Index: 3511711 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.5383. Min Act: -0.1700
Data Index: 3276904 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.5383. Min Act: -0.1700
Data Index: 6824305 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.5695. Min Act: -0.1700
Data Index: 2312803 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.5070. Min Act: -0.1700
Data Index: 6789525 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.4758. Min Act: -0.1700
Data Index: 328727 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.4758. Min Act: -0.1700
Data Index: 5464825 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.4133. Min Act: -0.1700
Data Index: 7860349 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.4445. Min Act: -0.1700
Data Index: 6421310 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0383. Min Range: -8.0383
Max Act: 7.4445. Min Act: -0.1700
Data Index: 6150832 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19