Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1523 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1308. Min Range: -4.1308
Max Act: 4.1308. Min Act: -0.1700
Data Index: 3847719 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1308. Min Range: -4.1308
Max Act: 4.0058. Min Act: -0.1700
Data Index: 6687015 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9745. Min Act: -0.1700
Data Index: 1720536 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9433. Min Act: -0.1700
Data Index: 756340 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9433. Min Act: -0.1700
Data Index: 7825528 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9433. Min Act: -0.1700
Data Index: 1280861 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8807. Min Act: -0.1700
Data Index: 5022405 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8495. Min Act: -0.1700
Data Index: 4767349 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8182. Min Act: -0.1700
Data Index: 947721 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8338. Min Act: -0.1700
Data Index: 7135093 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8182. Min Act: -0.1700
Data Index: 2846158 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8495. Min Act: -0.1700
Data Index: 2787657 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8495. Min Act: -0.1700
Data Index: 7115613 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8182. Min Act: -0.1700
Data Index: 2280623 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8338. Min Act: -0.1700
Data Index: 628572 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8182. Min Act: -0.1700
Data Index: 610686 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8338. Min Act: -0.1700
Data Index: 914492 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8026. Min Act: -0.1700
Data Index: 8388846 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8026. Min Act: -0.1700
Data Index: 5535672 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8026. Min Act: -0.1700
Data Index: 7158684 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19