Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4716 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2741. Min Range: -6.2741
Max Act: 6.2741. Min Act: -0.1700
Data Index: 1589985 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.9304. Min Act: -0.1700
Data Index: 6083156 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.7116. Min Act: -0.1700
Data Index: 2760310 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.6804. Min Act: -0.1700
Data Index: 1227947 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.6491. Min Act: -0.1700
Data Index: 1450868 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5866. Min Act: -0.1700
Data Index: 31556 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.6179. Min Act: -0.1700
Data Index: 7704827 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.6491. Min Act: -0.1700
Data Index: 3279227 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5866. Min Act: -0.1700
Data Index: 7854736 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.6179. Min Act: -0.1700
Data Index: 8773860 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5866. Min Act: -0.1700
Data Index: 3324221 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5866. Min Act: -0.1700
Data Index: 4887212 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5554. Min Act: -0.1700
Data Index: 523574 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5554. Min Act: -0.1700
Data Index: 7852109 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5554. Min Act: -0.1700
Data Index: 3120881 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5554. Min Act: -0.1700
Data Index: 4749926 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5554. Min Act: -0.1700
Data Index: 6399217 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5554. Min Act: -0.1700
Data Index: 363803 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5241. Min Act: -0.1700
Data Index: 6363579 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2741. Min Range: -6.2741
Max Act: 5.5241. Min Act: -0.1700
Data Index: 5955866 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19