Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.7200. Min Act: -0.1700
Data Index: 6243241 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.7513. Min Act: -0.1699
Data Index: 3937427 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.7200. Min Act: -0.1700
Data Index: 6837480 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.6888. Min Act: -0.1700
Data Index: 2710883 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5325. Min Act: -0.1700
Data Index: 3542715 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5638. Min Act: -0.1700
Data Index: 4703425 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5638. Min Act: -0.1700
Data Index: 2411756 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5638. Min Act: -0.1700
Data Index: 3569433 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5325. Min Act: -0.1700
Data Index: 1322053 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5325. Min Act: -0.1700
Data Index: 3269786 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 232602 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5013. Min Act: -0.1700
Data Index: 2423453 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 5943168 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4474031 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 7653711 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 7100868 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.5013. Min Act: -0.1700
Data Index: 1239091 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4747432 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 7033996 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7513. Min Range: -5.7513
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4520853 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19