Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4709 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0975. Min Range: -8.0975
Max Act: 8.0975. Min Act: -0.1700
Data Index: 3492596 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0975. Min Range: -8.0975
Max Act: 8.0663. Min Act: -0.1700
Data Index: 381704 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0975. Min Range: -8.0975
Max Act: 8.0038. Min Act: -0.1700
Data Index: 37171 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.9725. Min Act: -0.1700
Data Index: 2095944 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.9413. Min Act: -0.1700
Data Index: 3983181 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.9100. Min Act: -0.1700
Data Index: 7554063 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.7850. Min Act: -0.1700
Data Index: 6857142 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.7538. Min Act: -0.1700
Data Index: 1462339 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.7225. Min Act: -0.1700
Data Index: 395022 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.7538. Min Act: -0.1700
Data Index: 311315 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.6913. Min Act: -0.1700
Data Index: 3746671 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.6913. Min Act: -0.1700
Data Index: 8574238 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.6288. Min Act: -0.1700
Data Index: 7745512 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.6600. Min Act: -0.1700
Data Index: 6997705 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.5975. Min Act: -0.1700
Data Index: 180674 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.6288. Min Act: -0.1700
Data Index: 6957345 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.5975. Min Act: -0.1700
Data Index: 4647616 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.5975. Min Act: -0.1700
Data Index: 4886438 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.5975. Min Act: -0.1700
Data Index: 8690207 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0975. Min Range: -8.0975
Max Act: 7.5663. Min Act: -0.1700
Data Index: 444756 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19