Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5685. Min Act: -0.1700
Data Index: 1090025 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5685. Min Act: -0.1700
Data Index: 1090032 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5372. Min Act: -0.1700
Data Index: 6098122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5372. Min Act: -0.1700
Data Index: 702801 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5059. Min Act: -0.1700
Data Index: 5593926 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4745. Min Act: -0.1700
Data Index: 1090031 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5059. Min Act: -0.1700
Data Index: 4780284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4745. Min Act: -0.1700
Data Index: 5103959 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.5059. Min Act: -0.1700
Data Index: 3893220 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4745. Min Act: -0.1700
Data Index: 1562869 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 7518669 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 6843446 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 3765123 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 5765857 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4119. Min Act: -0.1700
Data Index: 1277203 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 3510954 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 7119660 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 10274 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4432. Min Act: -0.1700
Data Index: 1090024 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5685. Min Range: -3.5685
Max Act: 3.4119. Min Act: -0.1700
Data Index: 1090020 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19