Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 190 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.6982. Min Act: -0.1700
Data Index: 3345741 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.5732. Min Act: -0.1700
Data Index: 808879 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.2607. Min Act: -0.1700
Data Index: 7326660 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.1982. Min Act: -0.1700
Data Index: 1191945 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.1982. Min Act: -0.1700
Data Index: 7839942 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.1669. Min Act: -0.1700
Data Index: 7022831 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.1669. Min Act: -0.1700
Data Index: 4515410 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.1357. Min Act: -0.1700
Data Index: 5087465 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.1357. Min Act: -0.1700
Data Index: 8690276 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.1044. Min Act: -0.1700
Data Index: 2748474 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.0732. Min Act: -0.1700
Data Index: 5467621 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.0732. Min Act: -0.1700
Data Index: 1706685 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.0732. Min Act: -0.1700
Data Index: 1312909 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.0419. Min Act: -0.1700
Data Index: 5586936 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6982. Min Range: -6.6982
Max Act: 6.0107. Min Act: -0.1700
Data Index: 5646355 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6982. Min Range: -6.6982
Max Act: 5.9794. Min Act: -0.1700
Data Index: 5777406 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6982. Min Range: -6.6982
Max Act: 5.9794. Min Act: -0.1700
Data Index: 738505 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6982. Min Range: -6.6982
Max Act: 5.9794. Min Act: -0.1700
Data Index: 616391 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6982. Min Range: -6.6982
Max Act: 5.9482. Min Act: -0.1700
Data Index: 5323808 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6982. Min Range: -6.6982
Max Act: 5.9169. Min Act: -0.1700
Data Index: 7344667 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19