Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.4308. Min Act: -0.1700
Data Index: 3935371 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.2433. Min Act: -0.1700
Data Index: 4581853 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.1183. Min Act: -0.1700
Data Index: 8174784 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0871. Min Act: -0.1700
Data Index: 3894737 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0246. Min Act: -0.1700
Data Index: 2585830 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 297708 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 6790364 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 5258527 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9621. Min Act: -0.1700
Data Index: 2185931 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 8558460 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 4270789 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9621. Min Act: -0.1700
Data Index: 1672171 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9621. Min Act: -0.1700
Data Index: 6124382 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9621. Min Act: -0.1700
Data Index: 3348231 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 4003529 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 1512445 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6252535 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 2898566 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 4323624 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 1285111 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19