Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0442. Min Range: -7.0442
Max Act: 7.0442. Min Act: -0.1700
Data Index: 7757489 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.9504. Min Act: -0.1700
Data Index: 6952177 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.8567. Min Act: -0.1700
Data Index: 6605707 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.8254. Min Act: -0.1700
Data Index: 1471171 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.7942. Min Act: -0.1700
Data Index: 4000442 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.7942. Min Act: -0.1700
Data Index: 5867747 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.7942. Min Act: -0.1700
Data Index: 8039710 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.7629. Min Act: -0.1700
Data Index: 1212213 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.7317. Min Act: -0.1700
Data Index: 487237 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.7317. Min Act: -0.1700
Data Index: 3039014 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.7004. Min Act: -0.1700
Data Index: 1095981 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6692. Min Act: -0.1700
Data Index: 4332791 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6692. Min Act: -0.1700
Data Index: 411399 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6067. Min Act: -0.1700
Data Index: 2599980 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6379. Min Act: -0.1700
Data Index: 30506 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6379. Min Act: -0.1700
Data Index: 2159393 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6067. Min Act: -0.1700
Data Index: 5015128 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6379. Min Act: -0.1700
Data Index: 654795 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6067. Min Act: -0.1700
Data Index: 5223300 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0442. Min Range: -7.0442
Max Act: 6.6067. Min Act: -0.1700
Data Index: 4908535 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19