Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5894 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1877. Min Range: -6.1877
Max Act: 6.1877. Min Act: -0.1700
Data Index: 7470847 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1877. Min Range: -6.1877
Max Act: 6.1565. Min Act: -0.1700
Data Index: 6991614 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1877. Min Range: -6.1877
Max Act: 6.1252. Min Act: -0.1700
Data Index: 7803210 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1877. Min Range: -6.1877
Max Act: 6.0627. Min Act: -0.1700
Data Index: 7749854 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1877. Min Range: -6.1877
Max Act: 6.0002. Min Act: -0.1700
Data Index: 5247076 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1877. Min Range: -6.1877
Max Act: 6.0002. Min Act: -0.1700
Data Index: 8117806 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1877. Min Range: -6.1877
Max Act: 6.0002. Min Act: -0.1700
Data Index: 5395778 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.9690. Min Act: -0.1700
Data Index: 8558870 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.9690. Min Act: -0.1700
Data Index: 6751436 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.9065. Min Act: -0.1700
Data Index: 5090934 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.9065. Min Act: -0.1700
Data Index: 857671 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8752. Min Act: -0.1700
Data Index: 6357963 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8440. Min Act: -0.1700
Data Index: 7693353 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8440. Min Act: -0.1700
Data Index: 1020336 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8440. Min Act: -0.1700
Data Index: 3664098 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8440. Min Act: -0.1700
Data Index: 562702 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8127. Min Act: -0.1700
Data Index: 2727982 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8127. Min Act: -0.1700
Data Index: 2090331 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.8440. Min Act: -0.1700
Data Index: 338046 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1877. Min Range: -6.1877
Max Act: 5.7815. Min Act: -0.1700
Data Index: 7303084 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19