Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5045 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.9309. Min Act: -0.1700
Data Index: 2874055 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.7076. Min Act: -0.1700
Data Index: 572131 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6729. Min Act: -0.1700
Data Index: 3368804 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6903. Min Act: -0.1700
Data Index: 7995161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6903. Min Act: -0.1700
Data Index: 580678 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6555. Min Act: -0.1700
Data Index: 5242663 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6555. Min Act: -0.1700
Data Index: 2392285 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6381. Min Act: -0.1700
Data Index: 349012 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6207. Min Act: -0.1700
Data Index: 4175129 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6207. Min Act: -0.1700
Data Index: 6689331 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6207. Min Act: -0.1700
Data Index: 2682997 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6207. Min Act: -0.1700
Data Index: 7907483 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6207. Min Act: -0.1700
Data Index: 2200687 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.6032. Min Act: -0.1700
Data Index: 3443733 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.5857. Min Act: -0.1700
Data Index: 2225298 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.5857. Min Act: -0.1700
Data Index: 7440140 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.5683. Min Act: -0.1700
Data Index: 6945479 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.5683. Min Act: -0.1700
Data Index: 5856470 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.5508. Min Act: -0.1700
Data Index: 6173812 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9309. Min Range: -1.9309
Max Act: 1.5683. Min Act: -0.1700
Data Index: 6617474 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19