Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2198. Min Range: -8.2198
Max Act: 8.2198. Min Act: -0.1700
Data Index: 8347629 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.8448. Min Act: -0.1700
Data Index: 2945603 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.8135. Min Act: -0.1700
Data Index: 2976740 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.7198. Min Act: -0.1700
Data Index: 8304196 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.6260. Min Act: -0.1700
Data Index: 4321884 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.6573. Min Act: -0.1700
Data Index: 3066304 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5948. Min Act: -0.1700
Data Index: 2896731 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5948. Min Act: -0.1700
Data Index: 7098921 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5948. Min Act: -0.1700
Data Index: 3852403 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5948. Min Act: -0.1700
Data Index: 2635375 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5948. Min Act: -0.1700
Data Index: 1924698 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5948. Min Act: -0.1700
Data Index: 7982382 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5948. Min Act: -0.1700
Data Index: 3326451 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5635. Min Act: -0.1700
Data Index: 3341659 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5635. Min Act: -0.1700
Data Index: 4988989 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5635. Min Act: -0.1700
Data Index: 4069911 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5635. Min Act: -0.1700
Data Index: 4754613 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5323. Min Act: -0.1700
Data Index: 4485373 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.5010. Min Act: -0.1700
Data Index: 5839189 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2198. Min Range: -8.2198
Max Act: 7.4698. Min Act: -0.1700
Data Index: 4499117 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19