Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 406 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.4919. Min Act: -0.1700
Data Index: 4146934 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.4606. Min Act: -0.1700
Data Index: 2646473 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.4606. Min Act: -0.1700
Data Index: 1319328 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3979. Min Act: -0.1700
Data Index: 6049492 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3979. Min Act: -0.1700
Data Index: 4487986 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3665. Min Act: -0.1700
Data Index: 4856274 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3665. Min Act: -0.1700
Data Index: 4064615 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3352. Min Act: -0.1700
Data Index: 3039947 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3352. Min Act: -0.1700
Data Index: 5411700 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3352. Min Act: -0.1700
Data Index: 2789783 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3352. Min Act: -0.1700
Data Index: 3695838 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3352. Min Act: -0.1700
Data Index: 6932960 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3352. Min Act: -0.1700
Data Index: 1266446 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3665. Min Act: -0.1700
Data Index: 5166653 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3038. Min Act: -0.1700
Data Index: 1879422 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3038. Min Act: -0.1700
Data Index: 582688 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3038. Min Act: -0.1700
Data Index: 8727889 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.3038. Min Act: -0.1700
Data Index: 4560593 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.2724. Min Act: -0.1700
Data Index: 1118992 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4919. Min Range: -3.4919
Max Act: 3.2724. Min Act: -0.1700
Data Index: 6716103 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19