Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 498 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.1417. Min Act: -0.1700
Data Index: 4269991 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0792. Min Act: -0.1700
Data Index: 8242440 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0480. Min Act: -0.1700
Data Index: 4096201 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1734080 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1748524 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 91944 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1762569 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 2263347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1353767 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1273202 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 551030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1124686 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 379989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 607464 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 18452 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1111218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1091647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 1770827 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 518724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1417. Min Range: -7.1417
Max Act: 7.0167. Min Act: -0.1700
Data Index: 2153621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19