Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.9302. Min Act: -0.1700
Data Index: 1769420 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.6800. Min Act: -0.1700
Data Index: 4459409 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.6487. Min Act: -0.1700
Data Index: 3023745 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.5861. Min Act: -0.1700
Data Index: 2812867 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.6174. Min Act: -0.1700
Data Index: 113326 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.6174. Min Act: -0.1700
Data Index: 2466909 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.5548. Min Act: -0.1700
Data Index: 5707266 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.5548. Min Act: -0.1700
Data Index: 3090221 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.5548. Min Act: -0.1700
Data Index: 4923594 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.5235. Min Act: -0.1700
Data Index: 1728664 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.5548. Min Act: -0.1700
Data Index: 6009464 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4921. Min Act: -0.1700
Data Index: 2604334 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4765. Min Act: -0.1700
Data Index: 671953 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4608. Min Act: -0.1700
Data Index: 44392 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4765. Min Act: -0.1700
Data Index: 1038243 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4608. Min Act: -0.1700
Data Index: 7622751 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4608. Min Act: -0.1700
Data Index: 3194029 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4608. Min Act: -0.1700
Data Index: 35210 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4608. Min Act: -0.1700
Data Index: 2357373 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9302. Min Range: -3.9302
Max Act: 3.4608. Min Act: -0.1700
Data Index: 2913086 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19