Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.4790. Min Act: -0.1700
Data Index: 4326842 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.4790. Min Act: -0.1700
Data Index: 6546284 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.4165. Min Act: -0.1700
Data Index: 4107515 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.4165. Min Act: -0.1700
Data Index: 8405970 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3853. Min Act: -0.1700
Data Index: 928371 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3853. Min Act: -0.1700
Data Index: 4226288 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3853. Min Act: -0.1700
Data Index: 3243285 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3853. Min Act: -0.1700
Data Index: 2053957 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3540. Min Act: -0.1700
Data Index: 4765921 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3540. Min Act: -0.1700
Data Index: 7948396 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3540. Min Act: -0.1700
Data Index: 4840604 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3540. Min Act: -0.1700
Data Index: 523278 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.3228. Min Act: -0.1700
Data Index: 7957326 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.2915. Min Act: -0.1700
Data Index: 4375896 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.2915. Min Act: -0.1700
Data Index: 5844772 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.2915. Min Act: -0.1700
Data Index: 5463477 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.2915. Min Act: -0.1700
Data Index: 5323665 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.2915. Min Act: -0.1700
Data Index: 1996971 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.2915. Min Act: -0.1700
Data Index: 3193588 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4790. Min Range: -4.4790
Max Act: 4.2915. Min Act: -0.1700
Data Index: 6444117 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19