Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5981 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.6243. Min Act: -0.1700
Data Index: 7466141 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.6243. Min Act: -0.1700
Data Index: 7072565 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.4993. Min Act: -0.1700
Data Index: 3157491 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.4368. Min Act: -0.1700
Data Index: 342806 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.4368. Min Act: -0.1700
Data Index: 2666576 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.4368. Min Act: -0.1696
Data Index: 231805 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.3743. Min Act: -0.1700
Data Index: 520852 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.3743. Min Act: -0.1700
Data Index: 897004 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.3743. Min Act: -0.1700
Data Index: 1554781 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.3118. Min Act: -0.1700
Data Index: 2425745 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.3118. Min Act: -0.1700
Data Index: 7992800 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.3118. Min Act: -0.1700
Data Index: 6934955 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.3118. Min Act: -0.1700
Data Index: 3181067 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.2493. Min Act: -0.1700
Data Index: 4578898 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.1868. Min Act: -0.1700
Data Index: 3464063 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.1243. Min Act: -0.1699
Data Index: 4737220 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.1868. Min Act: -0.1699
Data Index: 3553902 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.2493. Min Act: -0.1700
Data Index: 497743 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.1243. Min Act: -0.1700
Data Index: 388668 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6243. Min Range: -12.6243
Max Act: 12.1243. Min Act: -0.1700
Data Index: 7009003 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19