Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4710. Min Act: -0.1700
Data Index: 8785157 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4710. Min Act: -0.1700
Data Index: 1141831 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4710. Min Act: -0.1700
Data Index: 641512 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4710. Min Act: -0.1700
Data Index: 3972841 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4396. Min Act: -0.1700
Data Index: 4819751 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4396. Min Act: -0.1700
Data Index: 6130758 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4396. Min Act: -0.1700
Data Index: 4362991 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4083. Min Act: -0.1700
Data Index: 4905872 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4083. Min Act: -0.1700
Data Index: 2228809 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4083. Min Act: -0.1700
Data Index: 765889 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4083. Min Act: -0.1700
Data Index: 2804622 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4083. Min Act: -0.1700
Data Index: 1514925 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.4083. Min Act: -0.1700
Data Index: 5699065 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.3769. Min Act: -0.1700
Data Index: 5235071 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.3769. Min Act: -0.1700
Data Index: 3124999 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.3456. Min Act: -0.1700
Data Index: 5632110 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.3456. Min Act: -0.1700
Data Index: 6843366 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.3456. Min Act: -0.1700
Data Index: 4846882 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.3299. Min Act: -0.1700
Data Index: 1758099 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4710. Min Range: -3.4710
Max Act: 3.3299. Min Act: -0.1700
Data Index: 7405814 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19