Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1856 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8882. Min Act: -0.1700
Data Index: 3222990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8570. Min Act: -0.1700
Data Index: 381725 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8570. Min Act: -0.1700
Data Index: 1376228 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8570. Min Act: -0.1700
Data Index: 517547 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8570. Min Act: -0.1700
Data Index: 6985712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8570. Min Act: -0.1700
Data Index: 1860758 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8257. Min Act: -0.1700
Data Index: 1658526 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8257. Min Act: -0.1700
Data Index: 1241925 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 1700011 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8257. Min Act: -0.1700
Data Index: 208010 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.8257. Min Act: -0.1700
Data Index: 584549 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 2508490 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 2168565 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7631. Min Act: -0.1700
Data Index: 4210656 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 654148 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 3488752 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 3222991 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 4514435 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 5047212 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8882. Min Range: -3.8882
Max Act: 3.7944. Min Act: -0.1700
Data Index: 7490274 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19