Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 216 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.6965. Min Act: -0.1700
Data Index: 4336784 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.5402. Min Act: -0.1700
Data Index: 4373028 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4465. Min Act: -0.1700
Data Index: 6512131 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.2590. Min Act: -0.1700
Data Index: 1378951 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.2590. Min Act: -0.1700
Data Index: 517420 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.2277. Min Act: -0.1700
Data Index: 1033481 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1965. Min Act: -0.1700
Data Index: 1461463 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1965. Min Act: -0.1700
Data Index: 7926234 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1340. Min Act: -0.1700
Data Index: 3688400 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1027. Min Act: -0.1700
Data Index: 7271481 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1027. Min Act: -0.1700
Data Index: 8731951 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1027. Min Act: -0.1700
Data Index: 3830348 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.0715. Min Act: -0.1700
Data Index: 3599668 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1027. Min Act: -0.1700
Data Index: 5541406 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.1027. Min Act: -0.1700
Data Index: 2327078 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.0715. Min Act: -0.1700
Data Index: 2040496 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.0715. Min Act: -0.1700
Data Index: 1209785 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.0715. Min Act: -0.1700
Data Index: 8015322 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.0715. Min Act: -0.1700
Data Index: 4862841 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.0715. Min Act: -0.1700
Data Index: 5603583 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19