Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3750 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.5164. Min Act: -0.1700
Data Index: 508140 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.4539. Min Act: -0.1700
Data Index: 4056112 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.4227. Min Act: -0.1700
Data Index: 4485581 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.3914. Min Act: -0.1700
Data Index: 6577967 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.3289. Min Act: -0.1700
Data Index: 8591294 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.3602. Min Act: -0.1700
Data Index: 5375753 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.3289. Min Act: -0.1700
Data Index: 5715894 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.3289. Min Act: -0.1700
Data Index: 1381364 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2977. Min Act: -0.1700
Data Index: 7201810 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2977. Min Act: -0.1700
Data Index: 7948245 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2977. Min Act: -0.1700
Data Index: 1448362 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2664. Min Act: -0.1700
Data Index: 6614803 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2664. Min Act: -0.1700
Data Index: 5208229 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2352. Min Act: -0.1700
Data Index: 217426 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2352. Min Act: -0.1700
Data Index: 365894 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2664. Min Act: -0.1700
Data Index: 5375749 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2352. Min Act: -0.1700
Data Index: 6953796 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2352. Min Act: -0.1700
Data Index: 1416762 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2352. Min Act: -0.1700
Data Index: 5111603 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5164. Min Range: -6.5164
Max Act: 6.2664. Min Act: -0.1700
Data Index: 508139 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19