Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 139 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0470. Min Range: -8.0470
Max Act: 8.0470. Min Act: -0.1700
Data Index: 3301849 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.9220. Min Act: -0.1700
Data Index: 4306325 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.8907. Min Act: -0.1700
Data Index: 5934340 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.8907. Min Act: -0.1700
Data Index: 7161198 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.8282. Min Act: -0.1700
Data Index: 7108213 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.8595. Min Act: -0.1700
Data Index: 2554296 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.8282. Min Act: -0.1700
Data Index: 7705009 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.7657. Min Act: -0.1700
Data Index: 3788295 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.7657. Min Act: -0.1700
Data Index: 435119 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.7657. Min Act: -0.1700
Data Index: 2571434 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.7657. Min Act: -0.1700
Data Index: 5571899 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.7345. Min Act: -0.1700
Data Index: 3009290 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.7032. Min Act: -0.1700
Data Index: 8061065 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.7032. Min Act: -0.1700
Data Index: 2925457 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.6720. Min Act: -0.1700
Data Index: 942782 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.6720. Min Act: -0.1700
Data Index: 3536957 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.6720. Min Act: -0.1700
Data Index: 5046903 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.6407. Min Act: -0.1700
Data Index: 1078837 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.5470. Min Act: -0.1700
Data Index: 2700267 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0470. Min Range: -8.0470
Max Act: 7.5470. Min Act: -0.1700
Data Index: 5923473 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19