Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2819. Min Act: -0.1700
Data Index: 5180417 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2819. Min Act: -0.1700
Data Index: 4405406 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2194. Min Act: -0.1700
Data Index: 4628459 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2819. Min Act: -0.1700
Data Index: 8572561 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2506. Min Act: -0.1700
Data Index: 7609281 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2506. Min Act: -0.1700
Data Index: 1980326 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2506. Min Act: -0.1700
Data Index: 2307180 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.2194. Min Act: -0.1700
Data Index: 1725445 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.1569. Min Act: -0.1700
Data Index: 2914435 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.1256. Min Act: -0.1700
Data Index: 5122400 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0944. Min Act: -0.1700
Data Index: 861464 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0944. Min Act: -0.1700
Data Index: 7661357 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0944. Min Act: -0.1700
Data Index: 5763694 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0631. Min Act: -0.1700
Data Index: 8723963 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0631. Min Act: -0.1700
Data Index: 5800619 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0944. Min Act: -0.1700
Data Index: 1798652 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0631. Min Act: -0.1700
Data Index: 1044629 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0631. Min Act: -0.1700
Data Index: 294478 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0006. Min Act: -0.1700
Data Index: 1472254 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2819. Min Range: -4.2819
Max Act: 4.0006. Min Act: -0.1700
Data Index: 595079 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19