Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.8988. Min Act: -0.1700
Data Index: 5118614 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.8675. Min Act: -0.1700
Data Index: 2843662 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.8050. Min Act: -0.1700
Data Index: 5892511 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 192906 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 4345437 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7425. Min Act: -0.1700
Data Index: 8287947 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 1399970 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7113. Min Act: -0.1700
Data Index: 1788529 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7113. Min Act: -0.1700
Data Index: 8643218 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7113. Min Act: -0.1700
Data Index: 4842884 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6488. Min Act: -0.1700
Data Index: 8394945 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6800. Min Act: -0.1700
Data Index: 5773041 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6488. Min Act: -0.1700
Data Index: 6079859 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6488. Min Act: -0.1700
Data Index: 8424643 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6488. Min Act: -0.1700
Data Index: 600363 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6175. Min Act: -0.1700
Data Index: 2296307 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6175. Min Act: -0.1700
Data Index: 1922145 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6175. Min Act: -0.1700
Data Index: 6163223 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6175. Min Act: -0.1700
Data Index: 6377668 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6175. Min Act: -0.1700
Data Index: 7841577 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19