Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.2606. Min Act: -0.1700
Data Index: 5937736 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.2293. Min Act: -0.1700
Data Index: 1836757 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.2606. Min Act: -0.1700
Data Index: 1562102 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.1356. Min Act: -0.1700
Data Index: 2126619 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.1043. Min Act: -0.1700
Data Index: 4603536 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.0731. Min Act: -0.1700
Data Index: 6575664 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.0418. Min Act: -0.1700
Data Index: 144083 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.0106. Min Act: -0.1700
Data Index: 923818 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.0106. Min Act: -0.1700
Data Index: 670013 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2606. Min Range: -7.2606
Max Act: 7.0106. Min Act: -0.1700
Data Index: 1348014 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9481. Min Act: -0.1700
Data Index: 4259680 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9793. Min Act: -0.1700
Data Index: 5228267 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9481. Min Act: -0.1700
Data Index: 7260293 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9793. Min Act: -0.1700
Data Index: 4944638 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9168. Min Act: -0.1700
Data Index: 8374710 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9168. Min Act: -0.1700
Data Index: 5393300 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9168. Min Act: -0.1700
Data Index: 1211890 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.9481. Min Act: -0.1700
Data Index: 994331 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.8856. Min Act: -0.1700
Data Index: 253142 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2606. Min Range: -7.2606
Max Act: 6.8856. Min Act: -0.1700
Data Index: 1181871 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19