Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.2113. Min Act: -0.1700
Data Index: 4499486 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.1281. Min Act: -0.1700
Data Index: 5680896 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.1281. Min Act: -0.1700
Data Index: 2104988 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.1281. Min Act: -0.1700
Data Index: 248675 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.1448. Min Act: -0.1700
Data Index: 3672217 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.1113. Min Act: -0.1700
Data Index: 2650280 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.1113. Min Act: -0.1700
Data Index: 2451311 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.1113. Min Act: -0.1700
Data Index: 4076112 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0778. Min Act: -0.1700
Data Index: 1845972 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0946. Min Act: -0.1700
Data Index: 5800473 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0946. Min Act: -0.1700
Data Index: 1214488 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0946. Min Act: -0.1700
Data Index: 8337283 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0946. Min Act: -0.1700
Data Index: 2490605 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0611. Min Act: -0.1700
Data Index: 4499485 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0611. Min Act: -0.1700
Data Index: 1067266 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0611. Min Act: -0.1700
Data Index: 2005681 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0611. Min Act: -0.1700
Data Index: 8337282 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0611. Min Act: -0.1700
Data Index: 5721635 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0611. Min Act: -0.1700
Data Index: 3512206 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2113. Min Range: -2.2113
Max Act: 2.0442. Min Act: -0.1700
Data Index: 5386556 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19