Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4747 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.4474. Min Act: -0.1700
Data Index: 6455599 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.3536. Min Act: -0.1700
Data Index: 6576920 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.3536. Min Act: -0.1700
Data Index: 7432212 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.2911. Min Act: -0.1700
Data Index: 5039630 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.2599. Min Act: -0.1700
Data Index: 7133845 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.2286. Min Act: -0.1700
Data Index: 2610762 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.1349. Min Act: -0.1700
Data Index: 740159 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.0724. Min Act: -0.1700
Data Index: 7774926 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.0411. Min Act: -0.1700
Data Index: 355689 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.0724. Min Act: -0.1700
Data Index: 308039 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.0411. Min Act: -0.1700
Data Index: 8058626 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.0411. Min Act: -0.1700
Data Index: 5424183 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4474. Min Range: -7.4474
Max Act: 6.9786. Min Act: -0.1700
Data Index: 7096701 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.0099. Min Act: -0.1700
Data Index: 3038195 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4474. Min Range: -7.4474
Max Act: 7.0099. Min Act: -0.1700
Data Index: 544148 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4474. Min Range: -7.4474
Max Act: 6.9786. Min Act: -0.1700
Data Index: 6034050 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4474. Min Range: -7.4474
Max Act: 6.9786. Min Act: -0.1700
Data Index: 2050532 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4474. Min Range: -7.4474
Max Act: 6.9474. Min Act: -0.1700
Data Index: 4648464 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4474. Min Range: -7.4474
Max Act: 6.9474. Min Act: -0.1700
Data Index: 5880572 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4474. Min Range: -7.4474
Max Act: 6.8849. Min Act: -0.1700
Data Index: 7233772 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19