Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2445 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.6583. Min Act: -0.1700
Data Index: 3995975 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.4395. Min Act: -0.1700
Data Index: 5898920 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.4395. Min Act: -0.1700
Data Index: 2845686 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.3770. Min Act: -0.1700
Data Index: 6411659 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.3145. Min Act: -0.1700
Data Index: 5289399 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.3145. Min Act: -0.1700
Data Index: 5736280 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.1583. Min Act: -0.1700
Data Index: 1804429 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.2208. Min Act: -0.1700
Data Index: 5220868 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.2520. Min Act: -0.1700
Data Index: 8636714 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.1583. Min Act: -0.1700
Data Index: 7446204 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.1270. Min Act: -0.1700
Data Index: 4591573 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.0958. Min Act: -0.1700
Data Index: 827049 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.1583. Min Act: -0.1700
Data Index: 3986632 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.1270. Min Act: -0.1700
Data Index: 2900077 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.0333. Min Act: -0.1700
Data Index: 8631470 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.0333. Min Act: -0.1700
Data Index: 2135624 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6583. Min Range: -8.6583
Max Act: 8.0020. Min Act: -0.1700
Data Index: 1458008 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6583. Min Range: -8.6583
Max Act: 7.9083. Min Act: -0.1700
Data Index: 8615381 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6583. Min Range: -8.6583
Max Act: 7.8145. Min Act: -0.1700
Data Index: 7024946 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6583. Min Range: -8.6583
Max Act: 7.8458. Min Act: -0.1700
Data Index: 5876942 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19