Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 548 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.5116. Min Act: -0.1700
Data Index: 1839512 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.4803. Min Act: -0.1700
Data Index: 7437100 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.4803. Min Act: -0.1700
Data Index: 4296614 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.2928. Min Act: -0.1700
Data Index: 4298049 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1991. Min Act: -0.1700
Data Index: 2314112 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.2303. Min Act: -0.1700
Data Index: 130776 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1366. Min Act: -0.1700
Data Index: 2816313 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1678. Min Act: -0.1700
Data Index: 3278941 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1991. Min Act: -0.1700
Data Index: 7434623 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1678. Min Act: -0.1700
Data Index: 7679318 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1366. Min Act: -0.1700
Data Index: 1617330 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1366. Min Act: -0.1700
Data Index: 5126260 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1366. Min Act: -0.1700
Data Index: 8310036 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1053. Min Act: -0.1700
Data Index: 3352304 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1053. Min Act: -0.1700
Data Index: 5231849 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1053. Min Act: -0.1700
Data Index: 3124130 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1053. Min Act: -0.1700
Data Index: 5811021 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.1366. Min Act: -0.1700
Data Index: 6995975 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.0428. Min Act: -0.1700
Data Index: 956618 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5116. Min Range: -5.5116
Max Act: 5.0428. Min Act: -0.1700
Data Index: 6862864 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19