Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1639 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0716. Min Range: -6.0716
Max Act: 6.0716. Min Act: -0.1700
Data Index: 1458227 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0716. Min Range: -6.0716
Max Act: 6.0716. Min Act: -0.1700
Data Index: 7871264 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.9778. Min Act: -0.1700
Data Index: 1343506 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.9466. Min Act: -0.1700
Data Index: 2630757 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.9153. Min Act: -0.1700
Data Index: 8627677 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.9153. Min Act: -0.1700
Data Index: 980657 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.9153. Min Act: -0.1700
Data Index: 5623204 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8528. Min Act: -0.1700
Data Index: 8317154 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8528. Min Act: -0.1700
Data Index: 2460595 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8528. Min Act: -0.1700
Data Index: 7350771 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8841. Min Act: -0.1700
Data Index: 1939654 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8528. Min Act: -0.1700
Data Index: 1939645 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8528. Min Act: -0.1700
Data Index: 8498561 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8528. Min Act: -0.1700
Data Index: 5971619 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8528. Min Act: -0.1700
Data Index: 7871242 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8216. Min Act: -0.1700
Data Index: 5868330 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8216. Min Act: -0.1700
Data Index: 2630760 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8216. Min Act: -0.1700
Data Index: 2278853 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.8216. Min Act: -0.1700
Data Index: 110845 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0716. Min Range: -6.0716
Max Act: 5.7903. Min Act: -0.1700
Data Index: 7277056 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19