Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0635. Min Range: -7.0635
Max Act: 7.0635. Min Act: -0.1700
Data Index: 5067885 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.9385. Min Act: -0.1700
Data Index: 5922933 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.8447. Min Act: -0.1700
Data Index: 5323326 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.8447. Min Act: -0.1700
Data Index: 4708812 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.7197. Min Act: -0.1700
Data Index: 2458983 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.6572. Min Act: -0.1700
Data Index: 4080616 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.5635. Min Act: -0.1700
Data Index: 7365746 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.5322. Min Act: -0.1700
Data Index: 7845316 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.5322. Min Act: -0.1700
Data Index: 7233404 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 7911538 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 4379107 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 2008190 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.5010. Min Act: -0.1700
Data Index: 281762 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.4697. Min Act: -0.1700
Data Index: 7129722 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.4697. Min Act: -0.1700
Data Index: 94396 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.4697. Min Act: -0.1700
Data Index: 5156921 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.4697. Min Act: -0.1700
Data Index: 2240888 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.4697. Min Act: -0.1700
Data Index: 8364174 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 8203734 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0635. Min Range: -7.0635
Max Act: 6.4385. Min Act: -0.1700
Data Index: 5216037 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19