Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 454 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.9793. Min Act: -0.1700
Data Index: 7786110 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.9793. Min Act: -0.1700
Data Index: 6664030 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.9793. Min Act: -0.1700
Data Index: 7439096 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.9480. Min Act: -0.1700
Data Index: 5849052 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.9480. Min Act: -0.1700
Data Index: 6693119 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.8230. Min Act: -0.1700
Data Index: 7612285 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.7605. Min Act: -0.1700
Data Index: 276915 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.7605. Min Act: -0.1700
Data Index: 3487314 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.7605. Min Act: -0.1700
Data Index: 2947067 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.7605. Min Act: -0.1700
Data Index: 5093931 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6980. Min Act: -0.1700
Data Index: 7749966 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6980. Min Act: -0.1700
Data Index: 6578385 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6980. Min Act: -0.1700
Data Index: 1755509 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6980. Min Act: -0.1700
Data Index: 8297287 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6668. Min Act: -0.1700
Data Index: 5395363 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6355. Min Act: -0.1700
Data Index: 4296907 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6668. Min Act: -0.1700
Data Index: 2366721 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6668. Min Act: -0.1700
Data Index: 5882807 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6355. Min Act: -0.1700
Data Index: 1634808 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9793. Min Range: -5.9793
Max Act: 5.6355. Min Act: -0.1700
Data Index: 5823320 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19