Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2355 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4872. Min Range: -6.4872
Max Act: 6.4872. Min Act: -0.1700
Data Index: 1851743 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4872. Min Range: -6.4872
Max Act: 6.3622. Min Act: -0.1700
Data Index: 7311346 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4872. Min Range: -6.4872
Max Act: 6.2685. Min Act: -0.1700
Data Index: 495230 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4872. Min Range: -6.4872
Max Act: 6.1747. Min Act: -0.1700
Data Index: 841341 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4872. Min Range: -6.4872
Max Act: 6.1122. Min Act: -0.1700
Data Index: 5966982 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4872. Min Range: -6.4872
Max Act: 6.0497. Min Act: -0.1700
Data Index: 7107639 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4872. Min Range: -6.4872
Max Act: 6.0185. Min Act: -0.1700
Data Index: 6640140 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.9872. Min Act: -0.1700
Data Index: 5844520 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.9872. Min Act: -0.1700
Data Index: 3095206 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.9247. Min Act: -0.1700
Data Index: 7809740 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.8935. Min Act: -0.1700
Data Index: 7107627 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.8935. Min Act: -0.1700
Data Index: 6923507 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.8622. Min Act: -0.1700
Data Index: 7805229 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.8622. Min Act: -0.1700
Data Index: 1991501 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.8622. Min Act: -0.1700
Data Index: 2595883 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.8622. Min Act: -0.1700
Data Index: 4779796 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.7997. Min Act: -0.1700
Data Index: 7249210 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.8622. Min Act: -0.1700
Data Index: 5293425 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.7997. Min Act: -0.1700
Data Index: 2325630 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4872. Min Range: -6.4872
Max Act: 5.7997. Min Act: -0.1700
Data Index: 4892658 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19