Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.3690. Min Act: -0.1700
Data Index: 5269297 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 856703 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0877. Min Act: -0.1700
Data Index: 484170 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0877. Min Act: -0.1700
Data Index: 5922097 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0565. Min Act: -0.1700
Data Index: 6681654 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0877. Min Act: -0.1700
Data Index: 5930849 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0565. Min Act: -0.1700
Data Index: 8053380 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9940. Min Act: -0.1700
Data Index: 482693 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 271983 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 6453640 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 663456 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 7461299 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1469387 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1182498 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 3684 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9002. Min Act: -0.1700
Data Index: 2662039 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7248299 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 482695 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 868694 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.8690. Min Act: -0.1700
Data Index: 1933720 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19