Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.7810. Min Act: -0.1700
Data Index: 889874 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.5622. Min Act: -0.1700
Data Index: 5326225 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.5310. Min Act: -0.1700
Data Index: 5711437 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.4060. Min Act: -0.1700
Data Index: 3101178 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.4372. Min Act: -0.1700
Data Index: 2088183 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.4060. Min Act: -0.1700
Data Index: 5446806 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3122. Min Act: -0.1700
Data Index: 4724381 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3122. Min Act: -0.1700
Data Index: 6775017 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3435. Min Act: -0.1700
Data Index: 2416213 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3122. Min Act: -0.1700
Data Index: 7285009 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3122. Min Act: -0.1700
Data Index: 7004489 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2497. Min Act: -0.1700
Data Index: 4321612 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2810. Min Act: -0.1700
Data Index: 1298163 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2810. Min Act: -0.1700
Data Index: 1083916 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2497. Min Act: -0.1700
Data Index: 6723845 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.1872. Min Act: -0.1700
Data Index: 6959387 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.1872. Min Act: -0.1700
Data Index: 2597004 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.1872. Min Act: -0.1700
Data Index: 5468541 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.1560. Min Act: -0.1700
Data Index: 3133344 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.1560. Min Act: -0.1700
Data Index: 220562 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19