Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.7295. Min Act: -0.1700
Data Index: 2883807 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.2920. Min Act: -0.1700
Data Index: 8626044 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.2295. Min Act: -0.1700
Data Index: 3661177 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.2295. Min Act: -0.1700
Data Index: 3870396 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.1670. Min Act: -0.1700
Data Index: 2187274 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.1357. Min Act: -0.1700
Data Index: 1612790 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.0732. Min Act: -0.1700
Data Index: 4402104 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.1045. Min Act: -0.1700
Data Index: 5196803 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7295. Min Range: -5.7295
Max Act: 5.0107. Min Act: -0.1700
Data Index: 7137074 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.9482. Min Act: -0.1700
Data Index: 4861926 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.9482. Min Act: -0.1700
Data Index: 8478380 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.9482. Min Act: -0.1700
Data Index: 2889870 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.9482. Min Act: -0.1700
Data Index: 4763909 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.9170. Min Act: -0.1700
Data Index: 239125 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.9170. Min Act: -0.1700
Data Index: 6912401 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.8857. Min Act: -0.1700
Data Index: 8165849 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.8857. Min Act: -0.1700
Data Index: 3750176 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.8545. Min Act: -0.1700
Data Index: 5935388 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.8232. Min Act: -0.1700
Data Index: 5561355 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7295. Min Range: -5.7295
Max Act: 4.8232. Min Act: -0.1700
Data Index: 2489151 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19