Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2649 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.7650. Min Act: -0.1700
Data Index: 2691482 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.6712. Min Act: -0.1700
Data Index: 2661227 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.6712. Min Act: -0.1700
Data Index: 7004212 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.5460. Min Act: -0.1700
Data Index: 5614096 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.5303. Min Act: -0.1700
Data Index: 7004218 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.5147. Min Act: -0.1700
Data Index: 7165166 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.5147. Min Act: -0.1700
Data Index: 1390245 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4833. Min Act: -0.1700
Data Index: 5305170 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4677. Min Act: -0.1700
Data Index: 1391780 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4677. Min Act: -0.1700
Data Index: 4580388 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4520. Min Act: -0.1700
Data Index: 993208 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4677. Min Act: -0.1700
Data Index: 4920239 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4520. Min Act: -0.1700
Data Index: 5315097 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4207. Min Act: -0.1700
Data Index: 5345293 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4520. Min Act: -0.1700
Data Index: 1359170 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.3893. Min Act: -0.1700
Data Index: 7294455 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4050. Min Act: -0.1700
Data Index: 879490 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.4050. Min Act: -0.1700
Data Index: 6040348 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.3736. Min Act: -0.1700
Data Index: 5575708 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7650. Min Range: -3.7650
Max Act: 3.3893. Min Act: -0.1700
Data Index: 7719829 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19