Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1697 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0375. Min Range: -4.0375
Max Act: 4.0375. Min Act: -0.1700
Data Index: 189396 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.9437. Min Act: -0.1700
Data Index: 8156129 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0375. Min Range: -4.0375
Max Act: 4.0063. Min Act: -0.1700
Data Index: 1266140 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.9437. Min Act: -0.1700
Data Index: 2364598 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.9125. Min Act: -0.1700
Data Index: 5439987 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.9125. Min Act: -0.1700
Data Index: 670342 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8812. Min Act: -0.1700
Data Index: 4280815 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8500. Min Act: -0.1700
Data Index: 7085678 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8500. Min Act: -0.1700
Data Index: 938077 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1938220 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8500. Min Act: -0.1700
Data Index: 7300127 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8187. Min Act: -0.1700
Data Index: 5273749 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1989800 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.8187. Min Act: -0.1700
Data Index: 6218717 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.7874. Min Act: -0.1700
Data Index: 4256346 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.7874. Min Act: -0.1700
Data Index: 1760094 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.7874. Min Act: -0.1700
Data Index: 2511626 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.7874. Min Act: -0.1700
Data Index: 270965 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.7561. Min Act: -0.1700
Data Index: 2353330 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0375. Min Range: -4.0375
Max Act: 3.7874. Min Act: -0.1700
Data Index: 2432432 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19