Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0885. Min Range: -7.0885
Max Act: 7.0885. Min Act: -0.1700
Data Index: 6809044 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.9322. Min Act: -0.1700
Data Index: 5833371 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3382047 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.7760. Min Act: -0.1700
Data Index: 3766618 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.6822. Min Act: -0.1700
Data Index: 1579950 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.6822. Min Act: -0.1700
Data Index: 8301385 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.6197. Min Act: -0.1700
Data Index: 1485437 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.5572. Min Act: -0.1700
Data Index: 2924774 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.5572. Min Act: -0.1700
Data Index: 7201520 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.5572. Min Act: -0.1700
Data Index: 7126905 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.5572. Min Act: -0.1700
Data Index: 7590309 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.5260. Min Act: -0.1700
Data Index: 2654106 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4947. Min Act: -0.1700
Data Index: 1790557 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4635. Min Act: -0.1700
Data Index: 2275681 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4947. Min Act: -0.1700
Data Index: 4923231 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4947. Min Act: -0.1700
Data Index: 3871557 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4947. Min Act: -0.1700
Data Index: 5183196 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4947. Min Act: -0.1700
Data Index: 7328270 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4635. Min Act: -0.1700
Data Index: 5201258 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0885. Min Range: -7.0885
Max Act: 6.4635. Min Act: -0.1700
Data Index: 4483090 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19