Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 269 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.5590. Min Act: -0.1700
Data Index: 1429734 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.5276. Min Act: -0.1700
Data Index: 6511067 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.4963. Min Act: -0.1700
Data Index: 679389 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.4650. Min Act: -0.1700
Data Index: 6511053 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.4650. Min Act: -0.1700
Data Index: 2835256 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.4337. Min Act: -0.1700
Data Index: 7776484 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.4023. Min Act: -0.1700
Data Index: 2356228 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.4337. Min Act: -0.1700
Data Index: 8514789 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.4337. Min Act: -0.1700
Data Index: 4257124 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3709. Min Act: -0.1700
Data Index: 639994 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3866. Min Act: -0.1700
Data Index: 6854441 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3396. Min Act: -0.1700
Data Index: 5300196 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3709. Min Act: -0.1700
Data Index: 4665198 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3396. Min Act: -0.1700
Data Index: 3525368 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3239. Min Act: -0.1700
Data Index: 256818 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3239. Min Act: -0.1700
Data Index: 5057599 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3082. Min Act: -0.1700
Data Index: 139726 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.3396. Min Act: -0.1700
Data Index: 4442607 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.2925. Min Act: -0.1700
Data Index: 2925827 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5590. Min Range: -3.5590
Max Act: 3.2925. Min Act: -0.1700
Data Index: 1914520 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19