Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 691 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.1601. Min Act: -0.1700
Data Index: 6973520 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.1250. Min Act: -0.1654
Data Index: 3328351 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.1075. Min Act: -0.1700
Data Index: 7888818 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.1075. Min Act: -0.1700
Data Index: 1429901 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0900. Min Act: -0.1700
Data Index: 4150602 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.1075. Min Act: -0.1700
Data Index: 7302794 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0900. Min Act: -0.1698
Data Index: 1595680 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0900. Min Act: -0.1699
Data Index: 3186208 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0725. Min Act: -0.1700
Data Index: 1503211 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0725. Min Act: -0.1700
Data Index: 1706588 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0725. Min Act: -0.1700
Data Index: 3442782 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0900. Min Act: -0.1700
Data Index: 5058128 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0725. Min Act: -0.1700
Data Index: 4636617 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0550. Min Act: -0.1700
Data Index: 1150736 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0550. Min Act: -0.1699
Data Index: 4061634 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0550. Min Act: -0.1700
Data Index: 7599117 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0550. Min Act: -0.1700
Data Index: 8692902 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0550. Min Act: -0.1700
Data Index: 6835883 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0550. Min Act: -0.1700
Data Index: 299358 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1601. Min Range: -1.1601
Max Act: 1.0202. Min Act: -0.1700
Data Index: 1051564 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19