Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 105 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.2264. Min Act: -0.1700
Data Index: 2863378 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.1327. Min Act: -0.1700
Data Index: 2658518 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.1014. Min Act: -0.1700
Data Index: 6784039 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.0389. Min Act: -0.1700
Data Index: 2775692 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9764. Min Act: -0.1700
Data Index: 7893117 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.0389. Min Act: -0.1700
Data Index: 5462416 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.0702. Min Act: -0.1700
Data Index: 558617 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2264. Min Range: -5.2264
Max Act: 5.0389. Min Act: -0.1700
Data Index: 3469968 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9764. Min Act: -0.1700
Data Index: 4717734 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9139. Min Act: -0.1700
Data Index: 3871114 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9139. Min Act: -0.1700
Data Index: 5699038 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9452. Min Act: -0.1700
Data Index: 4340592 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9452. Min Act: -0.1700
Data Index: 7356859 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9139. Min Act: -0.1700
Data Index: 4701672 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.8827. Min Act: -0.1700
Data Index: 4833590 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9452. Min Act: -0.1700
Data Index: 4354677 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.8827. Min Act: -0.1700
Data Index: 2050677 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9139. Min Act: -0.1700
Data Index: 6196411 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9139. Min Act: -0.1700
Data Index: 3641855 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2264. Min Range: -5.2264
Max Act: 4.9452. Min Act: -0.1700
Data Index: 3535614 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19