Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5093 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.9037. Min Act: -0.1700
Data Index: 3952922 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8725. Min Act: -0.1700
Data Index: 4780550 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8725. Min Act: -0.1700
Data Index: 355055 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8725. Min Act: -0.1700
Data Index: 4436864 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8725. Min Act: -0.1700
Data Index: 3971084 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 6019507 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 1011325 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 4647109 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 2331353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 4074754 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 1779397 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 7040404 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8412. Min Act: -0.1700
Data Index: 3476873 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8099. Min Act: -0.1700
Data Index: 3680125 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8099. Min Act: -0.1700
Data Index: 2029770 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8099. Min Act: -0.1700
Data Index: 3581993 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8099. Min Act: -0.1700
Data Index: 3554692 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.7786. Min Act: -0.1700
Data Index: 3507074 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.8099. Min Act: -0.1700
Data Index: 627349 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9037. Min Range: -3.9037
Max Act: 3.7786. Min Act: -0.1700
Data Index: 664615 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19