Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0380. Min Range: -8.0380
Max Act: 8.0380. Min Act: -0.1700
Data Index: 8100448 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.8817. Min Act: -0.1700
Data Index: 7703206 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.8505. Min Act: -0.1700
Data Index: 5594460 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.7567. Min Act: -0.1700
Data Index: 7262 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.7255. Min Act: -0.1700
Data Index: 3308406 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.6317. Min Act: -0.1700
Data Index: 285811 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.6317. Min Act: -0.1700
Data Index: 5935436 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.6317. Min Act: -0.1700
Data Index: 5547982 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.5692. Min Act: -0.1700
Data Index: 3501614 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.5692. Min Act: -0.1700
Data Index: 3772728 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.5380. Min Act: -0.1700
Data Index: 1773801 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.4442. Min Act: -0.1700
Data Index: 3914168 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.4442. Min Act: -0.1700
Data Index: 4112620 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.4130. Min Act: -0.1700
Data Index: 5878786 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.3505. Min Act: -0.1700
Data Index: 1550037 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.3192. Min Act: -0.1700
Data Index: 4849902 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.3192. Min Act: -0.1700
Data Index: 5744262 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.3192. Min Act: -0.1700
Data Index: 2078068 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.2880. Min Act: -0.1700
Data Index: 300322 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0380. Min Range: -8.0380
Max Act: 7.2880. Min Act: -0.1700
Data Index: 4666343 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19