Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2255 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0754. Min Range: -9.0754
Max Act: 9.0754. Min Act: -0.1700
Data Index: 7326869 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.7629. Min Act: -0.1700
Data Index: 2624160 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.6379. Min Act: -0.1700
Data Index: 6984155 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.6379. Min Act: -0.1700
Data Index: 1454939 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.4504. Min Act: -0.1700
Data Index: 1615223 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.3879. Min Act: -0.1700
Data Index: 7066475 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.3254. Min Act: -0.1700
Data Index: 8611990 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.3254. Min Act: -0.1700
Data Index: 8702962 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.3879. Min Act: -0.1700
Data Index: 4156647 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.3879. Min Act: -0.1700
Data Index: 160324 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.2629. Min Act: -0.1700
Data Index: 4678498 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.2629. Min Act: -0.1700
Data Index: 1133885 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.2629. Min Act: -0.1700
Data Index: 1992550 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.1691. Min Act: -0.1700
Data Index: 4922760 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.1691. Min Act: -0.1700
Data Index: 8266691 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.1379. Min Act: -0.1700
Data Index: 7131931 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.1379. Min Act: -0.1700
Data Index: 3491328 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.0754. Min Act: -0.1700
Data Index: 7439715 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.0441. Min Act: -0.1700
Data Index: 3280490 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0754. Min Range: -9.0754
Max Act: 8.0129. Min Act: -0.1700
Data Index: 6523304 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19