Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.5465. Min Act: -0.1700
Data Index: 1211448 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.4528. Min Act: -0.1700
Data Index: 8456134 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.4215. Min Act: -0.1700
Data Index: 6774588 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.4215. Min Act: -0.1700
Data Index: 3694134 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3903. Min Act: -0.1700
Data Index: 1266619 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3590. Min Act: -0.1700
Data Index: 3275190 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3277. Min Act: -0.1700
Data Index: 4924723 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3277. Min Act: -0.1700
Data Index: 4960248 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3277. Min Act: -0.1700
Data Index: 738020 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3277. Min Act: -0.1700
Data Index: 7817309 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3277. Min Act: -0.1700
Data Index: 8005883 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3277. Min Act: -0.1700
Data Index: 5674708 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.2965. Min Act: -0.1700
Data Index: 2830484 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.2965. Min Act: -0.1700
Data Index: 4608515 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.2965. Min Act: -0.1700
Data Index: 5777316 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.2965. Min Act: -0.1700
Data Index: 4178402 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.3277. Min Act: -0.1700
Data Index: 3174615 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.2965. Min Act: -0.1700
Data Index: 6344256 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.2965. Min Act: -0.1700
Data Index: 6102793 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5465. Min Range: -4.5465
Max Act: 4.2652. Min Act: -0.1700
Data Index: 1951099 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19