Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1116 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0984. Min Range: -6.0984
Max Act: 6.0984. Min Act: -0.1700
Data Index: 5130788 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0984. Min Range: -6.0984
Max Act: 6.0047. Min Act: -0.1700
Data Index: 7259135 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.9734. Min Act: -0.1700
Data Index: 4286746 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.8484. Min Act: -0.1700
Data Index: 7772051 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.8484. Min Act: -0.1700
Data Index: 3993812 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.8172. Min Act: -0.1700
Data Index: 7723625 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.8172. Min Act: -0.1700
Data Index: 3974179 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.7859. Min Act: -0.1700
Data Index: 5951600 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.7547. Min Act: -0.1700
Data Index: 1070224 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7156814 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2959619 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6922. Min Act: -0.1700
Data Index: 1563764 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6922. Min Act: -0.1700
Data Index: 4919365 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6609. Min Act: -0.1700
Data Index: 1613187 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6609. Min Act: -0.1700
Data Index: 6802455 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6609. Min Act: -0.1700
Data Index: 4043569 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6609. Min Act: -0.1700
Data Index: 3365791 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6297. Min Act: -0.1700
Data Index: 765827 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.6609. Min Act: -0.1700
Data Index: 2174015 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0984. Min Range: -6.0984
Max Act: 5.5984. Min Act: -0.1700
Data Index: 6517491 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19