Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 69 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2394681 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4865. Min Act: -0.1700
Data Index: 7231423 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4240. Min Act: -0.1700
Data Index: 6843843 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.2677. Min Act: -0.1700
Data Index: 4574859 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.2677. Min Act: -0.1700
Data Index: 392631 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.2677. Min Act: -0.1700
Data Index: 1991708 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.2365. Min Act: -0.1700
Data Index: 1143926 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.2052. Min Act: -0.1700
Data Index: 1318569 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.2052. Min Act: -0.1700
Data Index: 987043 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1427. Min Act: -0.1700
Data Index: 5760938 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1427. Min Act: -0.1700
Data Index: 3914800 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1427. Min Act: -0.1700
Data Index: 8007790 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1427. Min Act: -0.1700
Data Index: 6507511 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1427. Min Act: -0.1700
Data Index: 11085 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1427. Min Act: -0.1700
Data Index: 5932526 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1115. Min Act: -0.1700
Data Index: 3950013 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1115. Min Act: -0.1700
Data Index: 5593021 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1115. Min Act: -0.1700
Data Index: 8824714 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1115. Min Act: -0.1700
Data Index: 4126726 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.1115. Min Act: -0.1700
Data Index: 5827007 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19