Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 737 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.4873. Min Act: -0.1700
Data Index: 8107469 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.4873. Min Act: -0.1700
Data Index: 739031 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.4560. Min Act: -0.1700
Data Index: 1852293 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.4560. Min Act: -0.1700
Data Index: 1569889 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.4248. Min Act: -0.1700
Data Index: 3799240 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.4248. Min Act: -0.1700
Data Index: 3210787 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3935. Min Act: -0.1700
Data Index: 3509011 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3935. Min Act: -0.1700
Data Index: 5661672 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3935. Min Act: -0.1700
Data Index: 7881186 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3623. Min Act: -0.1700
Data Index: 3435164 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3623. Min Act: -0.1700
Data Index: 4998702 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3623. Min Act: -0.1700
Data Index: 653586 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3623. Min Act: -0.1700
Data Index: 4465705 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3310. Min Act: -0.1700
Data Index: 2751470 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.3310. Min Act: -0.1700
Data Index: 8713225 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.2998. Min Act: -0.1700
Data Index: 4389787 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.2998. Min Act: -0.1700
Data Index: 2358817 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.2998. Min Act: -0.1700
Data Index: 5221922 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.2998. Min Act: -0.1700
Data Index: 5556261 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4873. Min Range: -5.4873
Max Act: 5.2998. Min Act: -0.1700
Data Index: 534194 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19