Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.8890. Min Act: -0.1700
Data Index: 389822 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.7952. Min Act: -0.1700
Data Index: 4729680 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.7640. Min Act: -0.1700
Data Index: 1387117 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.7327. Min Act: -0.1700
Data Index: 7370557 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.7327. Min Act: -0.1700
Data Index: 1541730 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.7327. Min Act: -0.1700
Data Index: 8483364 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.7015. Min Act: -0.1700
Data Index: 3258840 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.7327. Min Act: -0.1700
Data Index: 1201304 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 586516 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 6613549 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 5235862 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 2595259 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 1520394 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6390. Min Act: -0.1700
Data Index: 847235 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 12805 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 5029512 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6390. Min Act: -0.1700
Data Index: 8475649 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6702. Min Act: -0.1700
Data Index: 5044313 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6390. Min Act: -0.1700
Data Index: 2119471 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8890. Min Range: -5.8890
Max Act: 5.6390. Min Act: -0.1700
Data Index: 6890332 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19