Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.5368. Min Act: -0.1700
Data Index: 7927365 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.5368. Min Act: -0.1700
Data Index: 2910548 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.5055. Min Act: -0.1700
Data Index: 4852341 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.3180. Min Act: -0.1700
Data Index: 5470461 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.2868. Min Act: -0.1700
Data Index: 6820775 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.2555. Min Act: -0.1700
Data Index: 7161711 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.2555. Min Act: -0.1700
Data Index: 2346846 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.2243. Min Act: -0.1700
Data Index: 1139359 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.2243. Min Act: -0.1700
Data Index: 1003937 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.1930. Min Act: -0.1700
Data Index: 6604377 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.1618. Min Act: -0.1700
Data Index: 1683465 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.1305. Min Act: -0.1700
Data Index: 1147965 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.1305. Min Act: -0.1700
Data Index: 6328503 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.0680. Min Act: -0.1700
Data Index: 6843261 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.0993. Min Act: -0.1700
Data Index: 2271106 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.0993. Min Act: -0.1700
Data Index: 3565734 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.0993. Min Act: -0.1700
Data Index: 1298769 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.0680. Min Act: -0.1700
Data Index: 622214 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.0680. Min Act: -0.1700
Data Index: 2201965 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5368. Min Range: -5.5368
Max Act: 5.0680. Min Act: -0.1700
Data Index: 2457774 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19