Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4550 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.9557. Min Act: -0.1700
Data Index: 7323701 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.9245. Min Act: -0.1700
Data Index: 6168612 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.8776. Min Act: -0.1700
Data Index: 6409034 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.8932. Min Act: -0.1700
Data Index: 3077891 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.8619. Min Act: -0.1700
Data Index: 4733454 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.8619. Min Act: -0.1700
Data Index: 7145350 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.8150. Min Act: -0.1700
Data Index: 8394946 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7525. Min Act: -0.1700
Data Index: 204036 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7681. Min Act: -0.1700
Data Index: 5401128 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7681. Min Act: -0.1700
Data Index: 8018448 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7681. Min Act: -0.1700
Data Index: 403039 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7212. Min Act: -0.1700
Data Index: 231409 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7369. Min Act: -0.1700
Data Index: 4404583 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7369. Min Act: -0.1700
Data Index: 6479571 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.7056. Min Act: -0.1700
Data Index: 3177064 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.6743. Min Act: -0.1700
Data Index: 155078 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.6586. Min Act: -0.1700
Data Index: 2353637 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.6586. Min Act: -0.1700
Data Index: 6625009 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.6430. Min Act: -0.1700
Data Index: 2335096 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9557. Min Range: -3.9557
Max Act: 3.6273. Min Act: -0.1700
Data Index: 2883337 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19