Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.4227. Min Act: -0.1700
Data Index: 5051165 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.4227. Min Act: -0.1700
Data Index: 8673171 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.3602. Min Act: -0.1700
Data Index: 8456872 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.2977. Min Act: -0.1700
Data Index: 2509427 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.2665. Min Act: -0.1700
Data Index: 1492486 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.2352. Min Act: -0.1700
Data Index: 6471638 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.2352. Min Act: -0.1700
Data Index: 486570 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.2040. Min Act: -0.1700
Data Index: 6758683 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1727. Min Act: -0.1700
Data Index: 3539879 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.2040. Min Act: -0.1700
Data Index: 3674013 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1727. Min Act: -0.1700
Data Index: 5950824 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1727. Min Act: -0.1700
Data Index: 7418525 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1415. Min Act: -0.1700
Data Index: 3534043 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1727. Min Act: -0.1700
Data Index: 493946 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1415. Min Act: -0.1700
Data Index: 2379529 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1415. Min Act: -0.1700
Data Index: 6527844 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1415. Min Act: -0.1700
Data Index: 281266 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1415. Min Act: -0.1700
Data Index: 5627129 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1415. Min Act: -0.1700
Data Index: 4243499 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1415. Min Act: -0.1700
Data Index: 1265875 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19