Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5403. Min Range: -8.5403
Max Act: 8.5403. Min Act: -0.1700
Data Index: 3300234 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5403. Min Range: -8.5403
Max Act: 8.4153. Min Act: -0.1700
Data Index: 5239405 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.9153. Min Act: -0.1700
Data Index: 5485822 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.9153. Min Act: -0.1700
Data Index: 5485823 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.8528. Min Act: -0.1700
Data Index: 3050654 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.6653. Min Act: -0.1700
Data Index: 157520 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.6340. Min Act: -0.1700
Data Index: 3858630 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.5715. Min Act: -0.1700
Data Index: 6844989 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.5715. Min Act: -0.1700
Data Index: 2075547 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4778. Min Act: -0.1700
Data Index: 3670959 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.5090. Min Act: -0.1700
Data Index: 7384730 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4778. Min Act: -0.1700
Data Index: 2034193 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4778. Min Act: -0.1700
Data Index: 5344166 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4778. Min Act: -0.1700
Data Index: 7532204 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4778. Min Act: -0.1700
Data Index: 6325289 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4778. Min Act: -0.1700
Data Index: 5100846 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4465. Min Act: -0.1700
Data Index: 2277455 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4465. Min Act: -0.1700
Data Index: 492844 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4153. Min Act: -0.1700
Data Index: 775006 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5403. Min Range: -8.5403
Max Act: 7.4153. Min Act: -0.1700
Data Index: 6711019 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19