Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.7926. Min Act: -0.1700
Data Index: 7067432 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.7301. Min Act: -0.1700
Data Index: 1397344 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6988. Min Act: -0.1700
Data Index: 4970803 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6676. Min Act: -0.1700
Data Index: 8040323 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 540386 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6676. Min Act: -0.1700
Data Index: 8486729 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 8500785 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 6931034 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 1764855 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 7262167 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 58367 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 7915587 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6051. Min Act: -0.1700
Data Index: 2990326 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6051. Min Act: -0.1700
Data Index: 563028 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6051. Min Act: -0.1700
Data Index: 5113403 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6051. Min Act: -0.1700
Data Index: 1457734 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 6901521 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6051. Min Act: -0.1700
Data Index: 4408738 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6363. Min Act: -0.1700
Data Index: 6901519 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7926. Min Range: -5.7926
Max Act: 5.6051. Min Act: -0.1700
Data Index: 6789590 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19