Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.6652. Min Act: -0.1700
Data Index: 909825 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3840. Min Act: -0.1700
Data Index: 6648830 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3215. Min Act: -0.1700
Data Index: 2437909 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.3527. Min Act: -0.1700
Data Index: 4181682 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.2590. Min Act: -0.1700
Data Index: 2033519 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.2590. Min Act: -0.1700
Data Index: 833203 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.2277. Min Act: -0.1700
Data Index: 8588241 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.1965. Min Act: -0.1700
Data Index: 1244736 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.1652. Min Act: -0.1700
Data Index: 4095108 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.1652. Min Act: -0.1700
Data Index: 5811063 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.1340. Min Act: -0.1700
Data Index: 4334075 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.1340. Min Act: -0.1700
Data Index: 7627141 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.1027. Min Act: -0.1700
Data Index: 6539441 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.1340. Min Act: -0.1700
Data Index: 5607896 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.0715. Min Act: -0.1700
Data Index: 4463492 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.0715. Min Act: -0.1700
Data Index: 5696198 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.0715. Min Act: -0.1700
Data Index: 8707756 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.0402. Min Act: -0.1700
Data Index: 3968836 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.0715. Min Act: -0.1700
Data Index: 7068235 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6652. Min Range: -6.6652
Max Act: 6.0402. Min Act: -0.1700
Data Index: 2186789 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19