Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.9956. Min Act: -0.1700
Data Index: 5186838 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.7144. Min Act: -0.1700
Data Index: 6496266 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.7144. Min Act: -0.1700
Data Index: 5062564 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6519. Min Act: -0.1700
Data Index: 6626041 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6519. Min Act: -0.1700
Data Index: 543393 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6519. Min Act: -0.1700
Data Index: 2770425 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6519. Min Act: -0.1700
Data Index: 6279865 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5894. Min Act: -0.1700
Data Index: 603499 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5269. Min Act: -0.1700
Data Index: 8172223 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5269. Min Act: -0.1700
Data Index: 8537056 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5269. Min Act: -0.1700
Data Index: 1902486 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4956. Min Act: -0.1700
Data Index: 2627010 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4644. Min Act: -0.1700
Data Index: 1395955 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4956. Min Act: -0.1700
Data Index: 3543272 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4644. Min Act: -0.1700
Data Index: 3262163 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4956. Min Act: -0.1700
Data Index: 7039257 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4644. Min Act: -0.1700
Data Index: 2048276 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4644. Min Act: -0.1700
Data Index: 1268178 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4331. Min Act: -0.1700
Data Index: 576424 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4331. Min Act: -0.1700
Data Index: 2263875 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19