Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2275. Min Range: -8.2275
Max Act: 8.2275. Min Act: -0.1700
Data Index: 2199565 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2275. Min Range: -8.2275
Max Act: 8.1650. Min Act: -0.1700
Data Index: 8344133 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.7900. Min Act: -0.1700
Data Index: 3836713 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.7588. Min Act: -0.1700
Data Index: 1200451 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.6963. Min Act: -0.1700
Data Index: 3836709 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.6963. Min Act: -0.1700
Data Index: 3836708 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.6650. Min Act: -0.1700
Data Index: 5475528 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.6025. Min Act: -0.1700
Data Index: 3836710 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.5400. Min Act: -0.1700
Data Index: 7202196 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.5400. Min Act: -0.1700
Data Index: 3836712 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.4775. Min Act: -0.1700
Data Index: 7240511 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.3838. Min Act: -0.1700
Data Index: 1706359 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.3838. Min Act: -0.1700
Data Index: 6981925 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.3838. Min Act: -0.1700
Data Index: 428282 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.3838. Min Act: -0.1700
Data Index: 3836714 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.3525. Min Act: -0.1700
Data Index: 1902356 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.4150. Min Act: -0.1700
Data Index: 4427124 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.3213. Min Act: -0.1700
Data Index: 6906297 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.2900. Min Act: -0.1700
Data Index: 588862 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2275. Min Range: -8.2275
Max Act: 7.3525. Min Act: -0.1700
Data Index: 764713 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19