Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2343. Min Range: -10.2343
Max Act: 10.2343. Min Act: -0.1700
Data Index: 4199169 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2343. Min Range: -10.2343
Max Act: 10.0468. Min Act: -0.1700
Data Index: 2498190 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2343. Min Range: -10.2343
Max Act: 10.1093. Min Act: -0.1700
Data Index: 3256223 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.9843. Min Act: -0.1700
Data Index: 5101414 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.9218. Min Act: -0.1700
Data Index: 8642222 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.8593. Min Act: -0.1700
Data Index: 2835789 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.7343. Min Act: -0.1700
Data Index: 196943 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.7968. Min Act: -0.1700
Data Index: 1467380 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.7968. Min Act: -0.1700
Data Index: 3101181 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.7968. Min Act: -0.1700
Data Index: 1668951 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.7343. Min Act: -0.1700
Data Index: 2239277 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.7343. Min Act: -0.1700
Data Index: 1802033 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.7343. Min Act: -0.1700
Data Index: 4395048 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.6718. Min Act: -0.1700
Data Index: 5807938 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.6093. Min Act: -0.1700
Data Index: 6644288 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.6718. Min Act: -0.1700
Data Index: 3836599 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.6718. Min Act: -0.1699
Data Index: 3970234 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.6093. Min Act: -0.1700
Data Index: 1112907 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.6718. Min Act: -0.1700
Data Index: 6407553 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2343. Min Range: -10.2343
Max Act: 9.6093. Min Act: -0.1700
Data Index: 6297797 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19