Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4469 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4025. Min Range: -6.4025
Max Act: 6.4025. Min Act: -0.1700
Data Index: 1701697 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4025. Min Range: -6.4025
Max Act: 6.3400. Min Act: -0.1700
Data Index: 2012973 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4025. Min Range: -6.4025
Max Act: 6.1213. Min Act: -0.1700
Data Index: 8505945 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4025. Min Range: -6.4025
Max Act: 6.0275. Min Act: -0.1700
Data Index: 576835 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.9963. Min Act: -0.1700
Data Index: 3696638 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.9963. Min Act: -0.1700
Data Index: 8259382 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.9338. Min Act: -0.1700
Data Index: 3679487 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.8713. Min Act: -0.1700
Data Index: 6687598 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.8400. Min Act: -0.1700
Data Index: 6986840 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.8088. Min Act: -0.1700
Data Index: 829914 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.8088. Min Act: -0.1700
Data Index: 8265286 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7775. Min Act: -0.1700
Data Index: 3984686 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7775. Min Act: -0.1700
Data Index: 893726 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7775. Min Act: -0.1700
Data Index: 8347093 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7463. Min Act: -0.1700
Data Index: 6878515 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7463. Min Act: -0.1700
Data Index: 7176614 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7463. Min Act: -0.1700
Data Index: 6815021 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7463. Min Act: -0.1700
Data Index: 7774795 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7150. Min Act: -0.1700
Data Index: 231165 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4025. Min Range: -6.4025
Max Act: 5.7150. Min Act: -0.1700
Data Index: 4749769 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19