Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0122. Min Range: -3.0122
Max Act: 3.0122. Min Act: -0.1700
Data Index: 4375756 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0122. Min Range: -3.0122
Max Act: 3.0122. Min Act: -0.1700
Data Index: 4375745 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 8502743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 2909502 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 5059349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 2252739 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 4028007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 1967388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 703027 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 4008466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9489. Min Act: -0.1700
Data Index: 1382880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 4310639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 907157 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 5517406 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 5619028 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 5923350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 6279716 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 7589797 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 8186509 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0122. Min Range: -3.0122
Max Act: 2.9173. Min Act: -0.1700
Data Index: 8233482 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19