Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.8421. Min Act: -0.1700
Data Index: 1275511 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.8109. Min Act: -0.1700
Data Index: 8138283 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.6234. Min Act: -0.1700
Data Index: 8293000 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.5921. Min Act: -0.1700
Data Index: 2840244 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.6234. Min Act: -0.1700
Data Index: 7800660 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.5921. Min Act: -0.1700
Data Index: 4553167 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.5609. Min Act: -0.1700
Data Index: 5351234 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.5609. Min Act: -0.1700
Data Index: 2674500 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.5609. Min Act: -0.1700
Data Index: 7839690 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.5609. Min Act: -0.1700
Data Index: 2597670 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.5296. Min Act: -0.1700
Data Index: 286496 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.4671. Min Act: -0.1700
Data Index: 7647372 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.4671. Min Act: -0.1700
Data Index: 5740775 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.3734. Min Act: -0.1700
Data Index: 5979919 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.3734. Min Act: -0.1700
Data Index: 2971492 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.4046. Min Act: -0.1700
Data Index: 1091506 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.3734. Min Act: -0.1700
Data Index: 919025 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.4046. Min Act: -0.1700
Data Index: 6408518 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.3421. Min Act: -0.1700
Data Index: 6611286 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8421. Min Range: -5.8421
Max Act: 5.3421. Min Act: -0.1700
Data Index: 7557075 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19