Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2068 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.8366. Min Act: -0.1700
Data Index: 7907959 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7741. Min Act: -0.1700
Data Index: 6081183 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7741. Min Act: -0.1700
Data Index: 1957927 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7897. Min Act: -0.1700
Data Index: 8339667 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7897. Min Act: -0.1700
Data Index: 2314281 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7428. Min Act: -0.1700
Data Index: 648178 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7584. Min Act: -0.1700
Data Index: 4536505 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7584. Min Act: -0.1700
Data Index: 6794524 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7741. Min Act: -0.1700
Data Index: 7687954 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7271. Min Act: -0.1700
Data Index: 4803900 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7271. Min Act: -0.1700
Data Index: 3712960 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7271. Min Act: -0.1700
Data Index: 5018111 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 6485724 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 1841289 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 325523 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 7045803 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 1541150 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7271. Min Act: -0.1700
Data Index: 6081175 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 19063 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 5250110 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19