Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5521. Min Range: -6.5521
Max Act: 6.5521. Min Act: -0.1700
Data Index: 1676706 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5521. Min Range: -6.5521
Max Act: 6.5521. Min Act: -0.1700
Data Index: 1676709 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.9896. Min Act: -0.1700
Data Index: 1676704 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.9584. Min Act: -0.1700
Data Index: 1676707 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.8646. Min Act: -0.1700
Data Index: 1676703 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.6146. Min Act: -0.1700
Data Index: 4522008 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.4896. Min Act: -0.1700
Data Index: 7705213 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.2709. Min Act: -0.1700
Data Index: 5213186 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.2396. Min Act: -0.1700
Data Index: 2797852 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.2396. Min Act: -0.1700
Data Index: 481016 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.2396. Min Act: -0.1700
Data Index: 3366124 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.2396. Min Act: -0.1700
Data Index: 7441610 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.2709. Min Act: -0.1700
Data Index: 7574160 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.1771. Min Act: -0.1700
Data Index: 2776795 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.2084. Min Act: -0.1700
Data Index: 2490537 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.1771. Min Act: -0.1700
Data Index: 2552914 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.1771. Min Act: -0.1700
Data Index: 6021316 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.1459. Min Act: -0.1700
Data Index: 7335499 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.1459. Min Act: -0.1700
Data Index: 5864618 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5521. Min Range: -6.5521
Max Act: 5.1459. Min Act: -0.1700
Data Index: 4235539 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19