Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4227 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.1883. Min Act: -0.1700
Data Index: 6566131 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0946. Min Act: -0.1700
Data Index: 6361650 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0946. Min Act: -0.1700
Data Index: 1922959 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0946. Min Act: -0.1700
Data Index: 7178244 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0633. Min Act: -0.1700
Data Index: 720520 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0633. Min Act: -0.1700
Data Index: 2112517 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0321. Min Act: -0.1700
Data Index: 8055438 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0321. Min Act: -0.1700
Data Index: 998159 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0321. Min Act: -0.1700
Data Index: 7734246 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0008. Min Act: -0.1700
Data Index: 6883718 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0008. Min Act: -0.1700
Data Index: 7883839 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0008. Min Act: -0.1700
Data Index: 4427266 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0008. Min Act: -0.1700
Data Index: 948248 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0008. Min Act: -0.1700
Data Index: 7585827 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1883. Min Range: -5.1883
Max Act: 5.0008. Min Act: -0.1700
Data Index: 4392585 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1883. Min Range: -5.1883
Max Act: 4.9696. Min Act: -0.1700
Data Index: 1981348 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1883. Min Range: -5.1883
Max Act: 4.9696. Min Act: -0.1700
Data Index: 6634801 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1883. Min Range: -5.1883
Max Act: 4.9696. Min Act: -0.1700
Data Index: 1759024 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1883. Min Range: -5.1883
Max Act: 4.9383. Min Act: -0.1700
Data Index: 818446 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1883. Min Range: -5.1883
Max Act: 4.9696. Min Act: -0.1700
Data Index: 1529208 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19