Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 848 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0759. Min Range: -3.0759
Max Act: 3.0759. Min Act: -0.1700
Data Index: 8716617 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0759. Min Range: -3.0759
Max Act: 3.0601. Min Act: -0.1700
Data Index: 4795336 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0759. Min Range: -3.0759
Max Act: 3.0444. Min Act: -0.1700
Data Index: 4717722 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.9970. Min Act: -0.1700
Data Index: 8716619 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.9337. Min Act: -0.1700
Data Index: 253588 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.9337. Min Act: -0.1700
Data Index: 1655010 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.9178. Min Act: -0.1700
Data Index: 8778802 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.9020. Min Act: -0.1700
Data Index: 6507554 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.9178. Min Act: -0.1700
Data Index: 787548 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8861. Min Act: -0.1700
Data Index: 4961263 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8703. Min Act: -0.1700
Data Index: 8716618 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8703. Min Act: -0.1700
Data Index: 8064926 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8861. Min Act: -0.1700
Data Index: 1638572 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8544. Min Act: -0.1700
Data Index: 4688444 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8703. Min Act: -0.1700
Data Index: 1271756 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8703. Min Act: -0.1700
Data Index: 4664822 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8226. Min Act: -0.1700
Data Index: 1245990 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8067. Min Act: -0.1700
Data Index: 1062944 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.8226. Min Act: -0.1700
Data Index: 7184768 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0759. Min Range: -3.0759
Max Act: 2.7907. Min Act: -0.1700
Data Index: 197711 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19