Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5267 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.3841. Min Act: -0.1700
Data Index: 5064302 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.3841. Min Act: -0.1700
Data Index: 3488856 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.3528. Min Act: -0.1700
Data Index: 1931354 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.2903. Min Act: -0.1700
Data Index: 7658421 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.3216. Min Act: -0.1700
Data Index: 3621127 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.2278. Min Act: -0.1700
Data Index: 1494962 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1966. Min Act: -0.1700
Data Index: 3031916 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1966. Min Act: -0.1700
Data Index: 5691057 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1653. Min Act: -0.1700
Data Index: 2162398 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1341. Min Act: -0.1700
Data Index: 1763351 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1341. Min Act: -0.1700
Data Index: 2739704 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1028. Min Act: -0.1700
Data Index: 3488855 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1028. Min Act: -0.1700
Data Index: 813066 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1028. Min Act: -0.1700
Data Index: 8694776 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1028. Min Act: -0.1700
Data Index: 2319423 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1028. Min Act: -0.1700
Data Index: 4319641 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1341. Min Act: -0.1700
Data Index: 3031914 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1028. Min Act: -0.1700
Data Index: 7176550 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.0716. Min Act: -0.1700
Data Index: 5860204 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3841. Min Range: -5.3841
Max Act: 5.1028. Min Act: -0.1700
Data Index: 6603510 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19