Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1392 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1583. Min Range: -5.1583
Max Act: 5.1583. Min Act: -0.1700
Data Index: 7300098 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1583. Min Range: -5.1583
Max Act: 5.1271. Min Act: -0.1700
Data Index: 7825884 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.9396. Min Act: -0.1700
Data Index: 669271 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.8458. Min Act: -0.1700
Data Index: 4568293 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.8146. Min Act: -0.1700
Data Index: 5882206 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.8146. Min Act: -0.1700
Data Index: 2834389 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.7521. Min Act: -0.1700
Data Index: 8717184 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.7208. Min Act: -0.1700
Data Index: 6911745 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.7521. Min Act: -0.1700
Data Index: 4713978 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.6896. Min Act: -0.1700
Data Index: 2143880 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.6583. Min Act: -0.1700
Data Index: 8689239 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.6896. Min Act: -0.1700
Data Index: 605364 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.6271. Min Act: -0.1700
Data Index: 6499934 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.5958. Min Act: -0.1700
Data Index: 386867 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.5958. Min Act: -0.1700
Data Index: 5093106 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.6271. Min Act: -0.1700
Data Index: 6344437 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.5958. Min Act: -0.1700
Data Index: 7248879 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.5958. Min Act: -0.1700
Data Index: 3942910 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.5646. Min Act: -0.1700
Data Index: 7141583 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1583. Min Range: -5.1583
Max Act: 4.5958. Min Act: -0.1700
Data Index: 1151144 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19