Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.4893. Min Act: -0.1700
Data Index: 1987432 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.3330. Min Act: -0.1700
Data Index: 2362023 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.3330. Min Act: -0.1700
Data Index: 2951961 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.3330. Min Act: -0.1700
Data Index: 6736729 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.2392. Min Act: -0.1700
Data Index: 4564164 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.2392. Min Act: -0.1700
Data Index: 7518613 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.1767. Min Act: -0.1700
Data Index: 8475895 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.1767. Min Act: -0.1700
Data Index: 6273040 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.1767. Min Act: -0.1700
Data Index: 3259903 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.1767. Min Act: -0.1700
Data Index: 6734098 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.1455. Min Act: -0.1700
Data Index: 629668 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.1142. Min Act: -0.1700
Data Index: 2741024 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.1142. Min Act: -0.1700
Data Index: 8047783 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.0830. Min Act: -0.1700
Data Index: 4828517 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.0830. Min Act: -0.1700
Data Index: 5627794 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.0517. Min Act: -0.1700
Data Index: 5899059 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.0830. Min Act: -0.1700
Data Index: 5241765 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.0830. Min Act: -0.1700
Data Index: 2259522 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.0517. Min Act: -0.1700
Data Index: 3194901 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4893. Min Range: -4.4893
Max Act: 4.0830. Min Act: -0.1700
Data Index: 6424761 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19