Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4599 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3633. Min Range: -6.3633
Max Act: 6.3633. Min Act: -0.1700
Data Index: 8451895 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3633. Min Range: -6.3633
Max Act: 6.2070. Min Act: -0.1700
Data Index: 1849292 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3633. Min Range: -6.3633
Max Act: 6.0820. Min Act: -0.1700
Data Index: 4397526 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3633. Min Range: -6.3633
Max Act: 6.0820. Min Act: -0.1700
Data Index: 2725765 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3633. Min Range: -6.3633
Max Act: 6.0820. Min Act: -0.1700
Data Index: 8269226 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3633. Min Range: -6.3633
Max Act: 6.0195. Min Act: -0.1700
Data Index: 4317885 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9883. Min Act: -0.1700
Data Index: 5105793 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9570. Min Act: -0.1700
Data Index: 5975452 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9883. Min Act: -0.1700
Data Index: 4931779 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9883. Min Act: -0.1700
Data Index: 8727113 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9570. Min Act: -0.1700
Data Index: 5247409 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9570. Min Act: -0.1700
Data Index: 20035 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9258. Min Act: -0.1700
Data Index: 5494975 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.9258. Min Act: -0.1700
Data Index: 7413496 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.8945. Min Act: -0.1700
Data Index: 4937366 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.8945. Min Act: -0.1700
Data Index: 5260263 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.8945. Min Act: -0.1700
Data Index: 3332875 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.8633. Min Act: -0.1700
Data Index: 3893354 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.8633. Min Act: -0.1700
Data Index: 7372407 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3633. Min Range: -6.3633
Max Act: 5.8633. Min Act: -0.1700
Data Index: 1617405 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19