Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8264. Min Range: -6.8264
Max Act: 6.8264. Min Act: -0.1700
Data Index: 7890696 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8264. Min Range: -6.8264
Max Act: 6.2951. Min Act: -0.1700
Data Index: 2271495 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8264. Min Range: -6.8264
Max Act: 6.1701. Min Act: -0.1700
Data Index: 5947120 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8264. Min Range: -6.8264
Max Act: 6.1701. Min Act: -0.1700
Data Index: 8823875 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8264. Min Range: -6.8264
Max Act: 6.0451. Min Act: -0.1700
Data Index: 5940979 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8264. Min Range: -6.8264
Max Act: 6.0764. Min Act: -0.1700
Data Index: 4436825 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.9201. Min Act: -0.1700
Data Index: 1370043 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4852700 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.9514. Min Act: -0.1700
Data Index: 7892245 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.9514. Min Act: -0.1700
Data Index: 3002449 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.9201. Min Act: -0.1700
Data Index: 8241338 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.8889. Min Act: -0.1700
Data Index: 4249201 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.8889. Min Act: -0.1700
Data Index: 3267770 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.7951. Min Act: -0.1700
Data Index: 6859974 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.8264. Min Act: -0.1700
Data Index: 4600125 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.7951. Min Act: -0.1700
Data Index: 3778237 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.7951. Min Act: -0.1700
Data Index: 7304385 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.7639. Min Act: -0.1700
Data Index: 5580476 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.7639. Min Act: -0.1700
Data Index: 4851460 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8264. Min Range: -6.8264
Max Act: 5.7326. Min Act: -0.1700
Data Index: 5673890 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19