Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2225. Min Range: -6.2225
Max Act: 6.2225. Min Act: -0.1700
Data Index: 3400486 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2225. Min Range: -6.2225
Max Act: 6.1600. Min Act: -0.1700
Data Index: 5514949 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2225. Min Range: -6.2225
Max Act: 6.0975. Min Act: -0.1700
Data Index: 6012040 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2225. Min Range: -6.2225
Max Act: 6.0975. Min Act: -0.1700
Data Index: 5341504 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2225. Min Range: -6.2225
Max Act: 6.0663. Min Act: -0.1700
Data Index: 5900454 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.9725. Min Act: -0.1700
Data Index: 1619363 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.9413. Min Act: -0.1700
Data Index: 1393981 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.8788. Min Act: -0.1700
Data Index: 3836667 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.8788. Min Act: -0.1700
Data Index: 481633 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.8475. Min Act: -0.1700
Data Index: 462404 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.7850. Min Act: -0.1700
Data Index: 825800 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.7538. Min Act: -0.1700
Data Index: 1810507 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.7225. Min Act: -0.1700
Data Index: 878557 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.7225. Min Act: -0.1700
Data Index: 6907385 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.6600. Min Act: -0.1700
Data Index: 5270320 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.6600. Min Act: -0.1700
Data Index: 45525 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.6288. Min Act: -0.1700
Data Index: 3726324 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.6288. Min Act: -0.1700
Data Index: 7147063 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.6288. Min Act: -0.1700
Data Index: 5307573 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2225. Min Range: -6.2225
Max Act: 5.6288. Min Act: -0.1700
Data Index: 2838693 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19