Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.6214. Min Act: -0.1700
Data Index: 3040626 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.5277. Min Act: -0.1700
Data Index: 2367657 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4964. Min Act: -0.1700
Data Index: 424500 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4964. Min Act: -0.1700
Data Index: 7893710 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4652. Min Act: -0.1700
Data Index: 2812859 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4652. Min Act: -0.1700
Data Index: 2055939 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4652. Min Act: -0.1700
Data Index: 5076886 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4339. Min Act: -0.1700
Data Index: 6719355 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4339. Min Act: -0.1700
Data Index: 394401 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4339. Min Act: -0.1700
Data Index: 4715855 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4027. Min Act: -0.1700
Data Index: 3801494 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4027. Min Act: -0.1700
Data Index: 4491429 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4027. Min Act: -0.1700
Data Index: 6281438 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4027. Min Act: -0.1700
Data Index: 4758380 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4027. Min Act: -0.1700
Data Index: 2663841 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.4027. Min Act: -0.1700
Data Index: 2186706 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.3714. Min Act: -0.1700
Data Index: 2186707 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.3714. Min Act: -0.1700
Data Index: 2758544 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.3714. Min Act: -0.1700
Data Index: 529500 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6214. Min Range: -5.6214
Max Act: 5.3402. Min Act: -0.1700
Data Index: 4904135 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19