Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5762 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1238. Min Range: -7.1238
Max Act: 7.1238. Min Act: -0.1700
Data Index: 6065308 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1238. Min Range: -7.1238
Max Act: 7.0925. Min Act: -0.1700
Data Index: 4798468 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1238. Min Range: -7.1238
Max Act: 7.0300. Min Act: -0.1700
Data Index: 5808536 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.9363. Min Act: -0.1700
Data Index: 5305145 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7488. Min Act: -0.1700
Data Index: 8235190 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7175. Min Act: -0.1700
Data Index: 8342482 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7175. Min Act: -0.1700
Data Index: 5881314 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.6863. Min Act: -0.1700
Data Index: 5406354 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.6550. Min Act: -0.1700
Data Index: 1959697 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.6863. Min Act: -0.1700
Data Index: 4180404 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.6550. Min Act: -0.1700
Data Index: 5481769 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5925. Min Act: -0.1700
Data Index: 4829521 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5925. Min Act: -0.1700
Data Index: 2189177 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5925. Min Act: -0.1700
Data Index: 5280495 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5925. Min Act: -0.1700
Data Index: 6274759 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5613. Min Act: -0.1700
Data Index: 4305526 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5613. Min Act: -0.1700
Data Index: 5633617 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5613. Min Act: -0.1700
Data Index: 4131807 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.4988. Min Act: -0.1700
Data Index: 234053 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5300. Min Act: -0.1700
Data Index: 5184639 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19