Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.5217. Min Act: -0.1700
Data Index: 8791888 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4690. Min Act: -0.1699
Data Index: 4013511 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4427. Min Act: -0.1578
Data Index: 16884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4251. Min Act: -0.1700
Data Index: 487032 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4251. Min Act: -0.1544
Data Index: 4568875 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4339. Min Act: -0.1700
Data Index: 2980399 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4162. Min Act: -0.1699
Data Index: 1827587 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4074. Min Act: -0.1699
Data Index: 1581350 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4074. Min Act: -0.1697
Data Index: 5078094 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4074. Min Act: -0.1700
Data Index: 7533011 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4162. Min Act: -0.1700
Data Index: 6078400 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.4074. Min Act: -0.1697
Data Index: 6144391 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3898. Min Act: -0.1700
Data Index: 1238217 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3898. Min Act: -0.1700
Data Index: 3046619 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3986. Min Act: -0.1700
Data Index: 6144389 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3810. Min Act: -0.1700
Data Index: 4989587 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3810. Min Act: -0.1700
Data Index: 3366444 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3722. Min Act: -0.1700
Data Index: 3336887 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3722. Min Act: -0.1700
Data Index: 5863868 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5217. Min Range: -1.5217
Max Act: 1.3722. Min Act: -0.1700
Data Index: 490580 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19