Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.9951. Min Act: -0.1700
Data Index: 8788666 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.9638. Min Act: -0.1700
Data Index: 3255516 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.9638. Min Act: -0.1700
Data Index: 2119324 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.9326. Min Act: -0.1700
Data Index: 8828351 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.9013. Min Act: -0.1700
Data Index: 374524 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.8701. Min Act: -0.1700
Data Index: 7146361 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.8388. Min Act: -0.1700
Data Index: 951710 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.7763. Min Act: -0.1700
Data Index: 3980727 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.7763. Min Act: -0.1700
Data Index: 1889995 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.7451. Min Act: -0.1700
Data Index: 2791565 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.7138. Min Act: -0.1700
Data Index: 7907802 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.6826. Min Act: -0.1700
Data Index: 5950380 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.6201. Min Act: -0.1700
Data Index: 3240486 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.6201. Min Act: -0.1700
Data Index: 483426 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.5888. Min Act: -0.1700
Data Index: 5534827 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.5888. Min Act: -0.1700
Data Index: 8398135 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.5888. Min Act: -0.1700
Data Index: 7221455 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.5576. Min Act: -0.1700
Data Index: 109675 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.5576. Min Act: -0.1700
Data Index: 5458645 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9951. Min Range: -5.9951
Max Act: 5.5263. Min Act: -0.1700
Data Index: 5035820 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19