Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2648 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.6563. Min Act: -0.1700
Data Index: 3307213 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.5626. Min Act: -0.1700
Data Index: 5775778 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.5313. Min Act: -0.1700
Data Index: 6569958 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4688. Min Act: -0.1700
Data Index: 4394616 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4376. Min Act: -0.1700
Data Index: 7542153 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4063. Min Act: -0.1700
Data Index: 6356097 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4063. Min Act: -0.1700
Data Index: 2931010 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3438. Min Act: -0.1700
Data Index: 7850896 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3751. Min Act: -0.1700
Data Index: 7166228 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3438. Min Act: -0.1700
Data Index: 712932 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3126. Min Act: -0.1700
Data Index: 6483719 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2813. Min Act: -0.1700
Data Index: 8815822 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2501. Min Act: -0.1700
Data Index: 599129 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2501. Min Act: -0.1700
Data Index: 5374136 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2813. Min Act: -0.1700
Data Index: 400102 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2188. Min Act: -0.1700
Data Index: 8653639 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3126. Min Act: -0.1700
Data Index: 4147538 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2188. Min Act: -0.1700
Data Index: 2188520 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2188. Min Act: -0.1700
Data Index: 4301540 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.1876. Min Act: -0.1700
Data Index: 4240877 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19