Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5216 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4936. Min Range: -6.4936
Max Act: 6.4936. Min Act: -0.1700
Data Index: 7347579 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4936. Min Range: -6.4936
Max Act: 6.1499. Min Act: -0.1700
Data Index: 3860296 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4936. Min Range: -6.4936
Max Act: 6.0561. Min Act: -0.1700
Data Index: 4505424 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4936. Min Range: -6.4936
Max Act: 6.0874. Min Act: -0.1700
Data Index: 8482161 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4936. Min Range: -6.4936
Max Act: 6.0561. Min Act: -0.1700
Data Index: 6243679 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4936. Min Range: -6.4936
Max Act: 6.0561. Min Act: -0.1700
Data Index: 3070116 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4936. Min Range: -6.4936
Max Act: 6.0249. Min Act: -0.1700
Data Index: 7021230 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.9936. Min Act: -0.1700
Data Index: 5835140 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2095885 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.9311. Min Act: -0.1700
Data Index: 785967 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.9311. Min Act: -0.1700
Data Index: 970190 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.9311. Min Act: -0.1700
Data Index: 1665794 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.9311. Min Act: -0.1700
Data Index: 3537223 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.8999. Min Act: -0.1700
Data Index: 6894840 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.8999. Min Act: -0.1700
Data Index: 1125106 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.8999. Min Act: -0.1700
Data Index: 8558086 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.8686. Min Act: -0.1700
Data Index: 534853 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.8999. Min Act: -0.1700
Data Index: 8713383 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.8374. Min Act: -0.1700
Data Index: 7114933 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4936. Min Range: -6.4936
Max Act: 5.8686. Min Act: -0.1700
Data Index: 1634544 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19