Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4793 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1639. Min Range: -9.1639
Max Act: 9.1639. Min Act: -0.1700
Data Index: 8407954 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.7264. Min Act: -0.1700
Data Index: 5814528 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.6639. Min Act: -0.1700
Data Index: 5736802 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.5389. Min Act: -0.1700
Data Index: 656831 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.5389. Min Act: -0.1700
Data Index: 2164966 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.5389. Min Act: -0.1700
Data Index: 5721659 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.5389. Min Act: -0.1700
Data Index: 1173462 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.4139. Min Act: -0.1700
Data Index: 8803496 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.4139. Min Act: -0.1700
Data Index: 7885900 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.4139. Min Act: -0.1700
Data Index: 7071430 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.3514. Min Act: -0.1700
Data Index: 577042 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.3514. Min Act: -0.1700
Data Index: 4243527 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2889. Min Act: -0.1700
Data Index: 1807340 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2889. Min Act: -0.1700
Data Index: 7465590 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2264. Min Act: -0.1700
Data Index: 8614526 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2264. Min Act: -0.1700
Data Index: 8732506 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2264. Min Act: -0.1700
Data Index: 763759 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2264. Min Act: -0.1700
Data Index: 2082954 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2264. Min Act: -0.1700
Data Index: 477127 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1639. Min Range: -9.1639
Max Act: 8.2264. Min Act: -0.1700
Data Index: 3502247 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19