Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4940 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2586. Min Act: -0.1700
Data Index: 6541063 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2273. Min Act: -0.1700
Data Index: 4601818 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2586. Min Act: -0.1700
Data Index: 3171790 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2273. Min Act: -0.1700
Data Index: 1253778 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.2273. Min Act: -0.1700
Data Index: 3044408 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1961. Min Act: -0.1700
Data Index: 3264110 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1961. Min Act: -0.1700
Data Index: 1007020 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3426458 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1648. Min Act: -0.1700
Data Index: 8114520 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1648. Min Act: -0.1700
Data Index: 4681474 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1648. Min Act: -0.1700
Data Index: 2934684 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 5538070 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 5119537 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1648. Min Act: -0.1700
Data Index: 5712340 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3116211 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 7552577 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 8366735 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 6856373 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 1388507 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2586. Min Range: -5.2586
Max Act: 5.1336. Min Act: -0.1700
Data Index: 476493 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19