Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.8753. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.4420. Min Act: -0.1700
Data Index: 6270324 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.4420. Min Act: -0.1700
Data Index: 4231913 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.4094. Min Act: -0.1700
Data Index: 3786665 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.4094. Min Act: -0.1700
Data Index: 8454786 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3931. Min Act: -0.1700
Data Index: 1651429 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3604. Min Act: -0.1700
Data Index: 101647 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3604. Min Act: -0.1700
Data Index: 4466446 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3440. Min Act: -0.1700
Data Index: 5383581 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3604. Min Act: -0.1700
Data Index: 1051189 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3440. Min Act: -0.1700
Data Index: 3072318 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3440. Min Act: -0.1700
Data Index: 567318 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3604. Min Act: -0.1700
Data Index: 7761964 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3440. Min Act: -0.1700
Data Index: 109869 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3440. Min Act: -0.1700
Data Index: 210670 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3276. Min Act: -0.1700
Data Index: 1738738 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3276. Min Act: -0.1700
Data Index: 8318826 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3112. Min Act: -0.1700
Data Index: 3776003 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3276. Min Act: -0.1700
Data Index: 1258666 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3112. Min Act: -0.1700
Data Index: 3085102 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19