Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 286 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.6991. Min Act: -0.1700
Data Index: 6187057 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.6991. Min Act: -0.1700
Data Index: 2149571 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.6366. Min Act: -0.1700
Data Index: 444546 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.5741. Min Act: -0.1700
Data Index: 5349546 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.5741. Min Act: -0.1700
Data Index: 5416087 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.6366. Min Act: -0.1700
Data Index: 5594997 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.5116. Min Act: -0.1700
Data Index: 12228 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.5116. Min Act: -0.1700
Data Index: 4935944 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 3502051 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 4880726 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 267520 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 1590663 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 4734212 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.3866. Min Act: -0.1700
Data Index: 4562983 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 5475091 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 5360108 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 4434999 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.3866. Min Act: -0.1700
Data Index: 2333791 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.3866. Min Act: -0.1700
Data Index: 8347358 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6991. Min Range: -8.6991
Max Act: 8.3241. Min Act: -0.1700
Data Index: 4161642 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19