Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.3250. Min Act: -0.1699
Data Index: 8374657 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.2921. Min Act: -0.1700
Data Index: 862863 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.2921. Min Act: -0.1700
Data Index: 3097702 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.2756. Min Act: -0.1700
Data Index: 1809916 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.2591. Min Act: -0.1700
Data Index: 5876360 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1929. Min Act: -0.1700
Data Index: 8725852 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1763. Min Act: -0.1700
Data Index: 5258635 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1597. Min Act: -0.1700
Data Index: 3253527 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1430. Min Act: -0.1697
Data Index: 7077770 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1430. Min Act: -0.1700
Data Index: 6523391 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1430. Min Act: -0.1700
Data Index: 7686815 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1430. Min Act: -0.1700
Data Index: 1245299 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1430. Min Act: -0.1700
Data Index: 6709615 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1430. Min Act: -0.1700
Data Index: 6411381 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1263. Min Act: -0.1700
Data Index: 4029970 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1263. Min Act: -0.1700
Data Index: 2022262 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1263. Min Act: -0.1700
Data Index: 3410712 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1096. Min Act: -0.1700
Data Index: 2270512 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1096. Min Act: -0.1700
Data Index: 7604255 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3250. Min Range: -2.3250
Max Act: 2.1096. Min Act: -0.1700
Data Index: 6784810 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19