Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5527. Min Range: -7.5527
Max Act: 7.5527. Min Act: -0.1700
Data Index: 2450517 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5527. Min Range: -7.5527
Max Act: 7.4902. Min Act: -0.1700
Data Index: 2796079 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5527. Min Range: -7.5527
Max Act: 7.0215. Min Act: -0.1700
Data Index: 8251904 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.9590. Min Act: -0.1700
Data Index: 777832 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.8965. Min Act: -0.1700
Data Index: 3048517 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.8965. Min Act: -0.1700
Data Index: 4601345 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.8965. Min Act: -0.1700
Data Index: 8331230 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.8340. Min Act: -0.1700
Data Index: 2346781 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.8027. Min Act: -0.1700
Data Index: 5227970 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.7402. Min Act: -0.1700
Data Index: 7571142 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.6777. Min Act: -0.1700
Data Index: 5820575 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.6777. Min Act: -0.1700
Data Index: 986249 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.6152. Min Act: -0.1700
Data Index: 2687399 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.5840. Min Act: -0.1700
Data Index: 1502777 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.5840. Min Act: -0.1700
Data Index: 804577 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.5527. Min Act: -0.1700
Data Index: 420236 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.5840. Min Act: -0.1700
Data Index: 1289407 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.5527. Min Act: -0.1700
Data Index: 7787089 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.5840. Min Act: -0.1700
Data Index: 2207055 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5527. Min Range: -7.5527
Max Act: 6.5527. Min Act: -0.1700
Data Index: 3871490 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19