Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.1235. Min Act: -0.1700
Data Index: 6766050 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0923. Min Act: -0.1700
Data Index: 6826853 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0923. Min Act: -0.1700
Data Index: 3409819 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0923. Min Act: -0.1700
Data Index: 5571447 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0610. Min Act: -0.1700
Data Index: 6727928 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0610. Min Act: -0.1700
Data Index: 7398764 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0610. Min Act: -0.1700
Data Index: 7973643 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0298. Min Act: -0.1700
Data Index: 3726551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0610. Min Act: -0.1700
Data Index: 969521 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0298. Min Act: -0.1700
Data Index: 2818850 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0298. Min Act: -0.1700
Data Index: 251663 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1689437 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0298. Min Act: -0.1700
Data Index: 1255483 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0923. Min Act: -0.1700
Data Index: 4439022 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0298. Min Act: -0.1700
Data Index: 8347857 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0298. Min Act: -0.1700
Data Index: 4875295 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1235. Min Range: -4.1235
Max Act: 4.0298. Min Act: -0.1700
Data Index: 2154759 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9673. Min Act: -0.1700
Data Index: 2765112 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9985. Min Act: -0.1700
Data Index: 342608 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1235. Min Range: -4.1235
Max Act: 3.9985. Min Act: -0.1700
Data Index: 3044908 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19