Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 267 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.9663. Min Act: -0.1700
Data Index: 3757605 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.9663. Min Act: -0.1700
Data Index: 1548294 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.9504. Min Act: -0.1700
Data Index: 714321 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.9346. Min Act: -0.1700
Data Index: 3125439 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.9188. Min Act: -0.1700
Data Index: 1416093 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.9188. Min Act: -0.1700
Data Index: 1986943 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.9188. Min Act: -0.1700
Data Index: 7161883 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8712. Min Act: -0.1700
Data Index: 4986762 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8870. Min Act: -0.1700
Data Index: 6848833 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8712. Min Act: -0.1700
Data Index: 692724 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8553. Min Act: -0.1700
Data Index: 6228464 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8076. Min Act: -0.1700
Data Index: 6604365 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8553. Min Act: -0.1700
Data Index: 4643957 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8394. Min Act: -0.1700
Data Index: 6561437 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8394. Min Act: -0.1700
Data Index: 2327118 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8235. Min Act: -0.1700
Data Index: 5532360 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8235. Min Act: -0.1700
Data Index: 2808747 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8394. Min Act: -0.1700
Data Index: 5190082 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8394. Min Act: -0.1700
Data Index: 491870 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9663. Min Range: -2.9663
Max Act: 2.8076. Min Act: -0.1700
Data Index: 6809371 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19