Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1379 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.7727. Min Act: -0.1700
Data Index: 7611507 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.7102. Min Act: -0.1700
Data Index: 7080812 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.5227. Min Act: -0.1700
Data Index: 3665183 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.4289. Min Act: -0.1700
Data Index: 2013963 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.3352. Min Act: -0.1700
Data Index: 654113 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.2727. Min Act: -0.1700
Data Index: 1965141 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.2727. Min Act: -0.1700
Data Index: 5371944 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.2414. Min Act: -0.1700
Data Index: 256352 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.2102. Min Act: -0.1700
Data Index: 4672248 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.2102. Min Act: -0.1700
Data Index: 5200672 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.0852. Min Act: -0.1700
Data Index: 4324506 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.1164. Min Act: -0.1700
Data Index: 8542139 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.0852. Min Act: -0.1700
Data Index: 7598778 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.0539. Min Act: -0.1700
Data Index: 8755307 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.0539. Min Act: -0.1700
Data Index: 5655586 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.0227. Min Act: -0.1700
Data Index: 1925319 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.0227. Min Act: -0.1700
Data Index: 5331143 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7727. Min Range: -6.7727
Max Act: 6.0227. Min Act: -0.1700
Data Index: 5977259 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7727. Min Range: -6.7727
Max Act: 5.9914. Min Act: -0.1700
Data Index: 7649371 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7727. Min Range: -6.7727
Max Act: 5.9914. Min Act: -0.1700
Data Index: 2231478 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19