Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 3358995 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4537. Min Act: -0.1700
Data Index: 3436413 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4225. Min Act: -0.1700
Data Index: 2078460 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4225. Min Act: -0.1700
Data Index: 8630736 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3600. Min Act: -0.1700
Data Index: 2633452 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3287. Min Act: -0.1700
Data Index: 7678520 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3287. Min Act: -0.1700
Data Index: 2936199 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2662. Min Act: -0.1700
Data Index: 2539750 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2662. Min Act: -0.1700
Data Index: 6108183 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2037. Min Act: -0.1700
Data Index: 374752 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2037. Min Act: -0.1700
Data Index: 4018803 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 1027381 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 7941748 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 5178264 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1100. Min Act: -0.1700
Data Index: 674893 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.0787. Min Act: -0.1700
Data Index: 2227155 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.0787. Min Act: -0.1700
Data Index: 8027556 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.0787. Min Act: -0.1700
Data Index: 6760575 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.0475. Min Act: -0.1700
Data Index: 6256083 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.0162. Min Act: -0.1700
Data Index: 5454796 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19