Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.4279. Min Act: -0.1700
Data Index: 5938957 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3654. Min Act: -0.1700
Data Index: 7278245 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3654. Min Act: -0.1700
Data Index: 13978 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3341. Min Act: -0.1700
Data Index: 2295140 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3341. Min Act: -0.1700
Data Index: 5117083 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3029. Min Act: -0.1700
Data Index: 4647756 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3029. Min Act: -0.1700
Data Index: 8499982 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3029. Min Act: -0.1700
Data Index: 7487924 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3029. Min Act: -0.1700
Data Index: 1826746 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.3341. Min Act: -0.1700
Data Index: 3252838 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2716. Min Act: -0.1700
Data Index: 7671649 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 1309200 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 8603142 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 393227 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 5766815 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 1703565 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 6341354 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 8353135 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2403. Min Act: -0.1700
Data Index: 8174501 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4279. Min Range: -4.4279
Max Act: 4.2091. Min Act: -0.1700
Data Index: 2435414 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19