Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 973 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2232. Min Range: -5.2232
Max Act: 5.2232. Min Act: -0.1700
Data Index: 8378416 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2232. Min Range: -5.2232
Max Act: 5.1294. Min Act: -0.1700
Data Index: 3646350 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2232. Min Range: -5.2232
Max Act: 5.0982. Min Act: -0.1700
Data Index: 2095559 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2232. Min Range: -5.2232
Max Act: 5.0357. Min Act: -0.1700
Data Index: 3719107 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2232. Min Range: -5.2232
Max Act: 5.0357. Min Act: -0.1700
Data Index: 2735729 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2232. Min Range: -5.2232
Max Act: 5.0357. Min Act: -0.1700
Data Index: 7196680 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2232. Min Range: -5.2232
Max Act: 5.0044. Min Act: -0.1700
Data Index: 2910929 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9732. Min Act: -0.1700
Data Index: 4208112 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9419. Min Act: -0.1700
Data Index: 5322475 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9419. Min Act: -0.1700
Data Index: 1733657 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9419. Min Act: -0.1700
Data Index: 7720026 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9419. Min Act: -0.1700
Data Index: 2001783 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9107. Min Act: -0.1700
Data Index: 4766078 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9419. Min Act: -0.1700
Data Index: 239514 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9107. Min Act: -0.1700
Data Index: 6545236 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9107. Min Act: -0.1700
Data Index: 1995683 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9107. Min Act: -0.1700
Data Index: 7876483 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9107. Min Act: -0.1700
Data Index: 5648340 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9107. Min Act: -0.1700
Data Index: 7317770 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2232. Min Range: -5.2232
Max Act: 4.9419. Min Act: -0.1700
Data Index: 827074 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19