Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5520 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.7100. Min Act: -0.1700
Data Index: 6993993 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.6753. Min Act: -0.1700
Data Index: 6978199 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.6579. Min Act: -0.1670
Data Index: 1051939 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.6405. Min Act: -0.1700
Data Index: 2862679 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.6056. Min Act: -0.1700
Data Index: 988049 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.5706. Min Act: -0.1700
Data Index: 442777 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.5181. Min Act: -0.1700
Data Index: 2929320 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.5005. Min Act: -0.1699
Data Index: 6607765 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4830. Min Act: -0.1698
Data Index: 6701802 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4654. Min Act: -0.1693
Data Index: 180585 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4654. Min Act: -0.1685
Data Index: 7434470 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4478. Min Act: -0.1687
Data Index: 5098266 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4478. Min Act: -0.1697
Data Index: 1342297 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4126. Min Act: -0.1699
Data Index: 3184933 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4302. Min Act: -0.1700
Data Index: 4822712 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4126. Min Act: -0.1699
Data Index: 3022575 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4302. Min Act: -0.1700
Data Index: 7835466 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4126. Min Act: -0.1700
Data Index: 5273601 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.4126. Min Act: -0.1693
Data Index: 3958101 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7100. Min Range: -1.7100
Max Act: 1.3773. Min Act: -0.1699
Data Index: 3053944 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19