Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5064 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.9561. Min Act: -0.1700
Data Index: 8289539 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.7061. Min Act: -0.1700
Data Index: 6590646 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.6749. Min Act: -0.1700
Data Index: 4714438 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.6749. Min Act: -0.1700
Data Index: 4147283 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.6436. Min Act: -0.1700
Data Index: 8363660 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.6436. Min Act: -0.1700
Data Index: 706556 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.6124. Min Act: -0.1700
Data Index: 1668757 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.6436. Min Act: -0.1700
Data Index: 4193041 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.6436. Min Act: -0.1700
Data Index: 8661098 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5811. Min Act: -0.1700
Data Index: 4897320 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5811. Min Act: -0.1700
Data Index: 1338717 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5811. Min Act: -0.1700
Data Index: 5436117 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5811. Min Act: -0.1700
Data Index: 2443785 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5499. Min Act: -0.1700
Data Index: 3707340 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.4874. Min Act: -0.1700
Data Index: 5499067 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5186. Min Act: -0.1700
Data Index: 742755 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5186. Min Act: -0.1700
Data Index: 8678294 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5186. Min Act: -0.1700
Data Index: 214676 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5186. Min Act: -0.1700
Data Index: 8795932 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9561. Min Range: -5.9561
Max Act: 5.5186. Min Act: -0.1700
Data Index: 2524876 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19