Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.8443. Min Act: -0.1700
Data Index: 7930383 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.7817. Min Act: -0.1700
Data Index: 1785853 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.7817. Min Act: -0.1700
Data Index: 199366 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.7817. Min Act: -0.1700
Data Index: 3425823 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.7817. Min Act: -0.1700
Data Index: 5188283 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.7504. Min Act: -0.1700
Data Index: 7353916 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.7192. Min Act: -0.1700
Data Index: 6298825 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.6879. Min Act: -0.1700
Data Index: 4043038 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.6879. Min Act: -0.1700
Data Index: 2639165 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.6879. Min Act: -0.1700
Data Index: 4152770 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.6566. Min Act: -0.1700
Data Index: 6032161 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.6566. Min Act: -0.1700
Data Index: 426470 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.6566. Min Act: -0.1700
Data Index: 5246809 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.6253. Min Act: -0.1700
Data Index: 7281642 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.5940. Min Act: -0.1700
Data Index: 8274798 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.5940. Min Act: -0.1700
Data Index: 6795667 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.5783. Min Act: -0.1700
Data Index: 2250637 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.5940. Min Act: -0.1700
Data Index: 8617500 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.5627. Min Act: -0.1700
Data Index: 4474261 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8443. Min Range: -3.8443
Max Act: 3.5470. Min Act: -0.1700
Data Index: 8593390 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19