Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.9308. Min Act: -0.1700
Data Index: 1107367 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.7433. Min Act: -0.1700
Data Index: 128762 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.7120. Min Act: -0.1700
Data Index: 1041182 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.7120. Min Act: -0.1700
Data Index: 5799765 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.7433. Min Act: -0.1700
Data Index: 5329966 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.6808. Min Act: -0.1700
Data Index: 900496 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.6495. Min Act: -0.1700
Data Index: 8701541 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.6183. Min Act: -0.1700
Data Index: 4168711 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.6183. Min Act: -0.1700
Data Index: 3587510 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5870. Min Act: -0.1700
Data Index: 5935210 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5558. Min Act: -0.1700
Data Index: 753228 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5558. Min Act: -0.1700
Data Index: 3135757 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5558. Min Act: -0.1700
Data Index: 114403 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5558. Min Act: -0.1700
Data Index: 8100113 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5558. Min Act: -0.1700
Data Index: 7840324 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5558. Min Act: -0.1700
Data Index: 1795647 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5245. Min Act: -0.1700
Data Index: 3717981 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5245. Min Act: -0.1700
Data Index: 4630647 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.5245. Min Act: -0.1700
Data Index: 3741160 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9308. Min Range: -4.9308
Max Act: 4.4933. Min Act: -0.1700
Data Index: 2053138 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19