Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5837 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.5313. Min Act: -0.1700
Data Index: 6217480 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.5313. Min Act: -0.1700
Data Index: 2645592 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.5313. Min Act: -0.1700
Data Index: 8331217 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.4688. Min Act: -0.1700
Data Index: 722711 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.4375. Min Act: -0.1700
Data Index: 3400692 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.4375. Min Act: -0.1700
Data Index: 487404 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.3750. Min Act: -0.1700
Data Index: 6535206 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.3438. Min Act: -0.1700
Data Index: 5623550 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.3438. Min Act: -0.1700
Data Index: 7897854 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.3125. Min Act: -0.1700
Data Index: 5541621 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.3125. Min Act: -0.1700
Data Index: 5307893 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.3125. Min Act: -0.1700
Data Index: 1300782 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.2813. Min Act: -0.1700
Data Index: 3531130 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.3125. Min Act: -0.1700
Data Index: 4213608 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.2813. Min Act: -0.1700
Data Index: 8337059 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.2813. Min Act: -0.1700
Data Index: 7188419 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.2813. Min Act: -0.1700
Data Index: 8359378 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.2813. Min Act: -0.1700
Data Index: 1271154 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.2500. Min Act: -0.1700
Data Index: 7792526 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5313. Min Range: -4.5313
Max Act: 4.2500. Min Act: -0.1700
Data Index: 1049810 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19