Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1464 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3304. Min Range: -7.3304
Max Act: 7.3304. Min Act: -0.1700
Data Index: 2762548 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.8304. Min Act: -0.1700
Data Index: 6788976 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.8304. Min Act: -0.1700
Data Index: 264353 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.7992. Min Act: -0.1700
Data Index: 4862469 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.7992. Min Act: -0.1700
Data Index: 8510611 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.7679. Min Act: -0.1700
Data Index: 1610402 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.7679. Min Act: -0.1700
Data Index: 5579870 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.5492. Min Act: -0.1700
Data Index: 468343 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.5492. Min Act: -0.1700
Data Index: 6580220 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.5179. Min Act: -0.1700
Data Index: 1913712 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.4867. Min Act: -0.1700
Data Index: 1251575 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.5179. Min Act: -0.1700
Data Index: 948964 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.5179. Min Act: -0.1700
Data Index: 6727032 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.4554. Min Act: -0.1700
Data Index: 3160691 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.4554. Min Act: -0.1700
Data Index: 6622138 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.4242. Min Act: -0.1700
Data Index: 4492263 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.4242. Min Act: -0.1700
Data Index: 4765457 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.4242. Min Act: -0.1700
Data Index: 7826822 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.4242. Min Act: -0.1700
Data Index: 4446932 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3304. Min Range: -7.3304
Max Act: 6.3617. Min Act: -0.1700
Data Index: 196060 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19