Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3675 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0049. Min Range: -7.0049
Max Act: 7.0049. Min Act: -0.1700
Data Index: 8506659 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.9424. Min Act: -0.1700
Data Index: 2467593 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.7549. Min Act: -0.1700
Data Index: 7587463 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.7549. Min Act: -0.1700
Data Index: 8707454 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.7862. Min Act: -0.1700
Data Index: 5561571 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.7549. Min Act: -0.1700
Data Index: 4299652 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 1825811 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6924. Min Act: -0.1700
Data Index: 4473711 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6299. Min Act: -0.1700
Data Index: 4192258 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 7066415 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 2449328 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 6079585 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.5987. Min Act: -0.1700
Data Index: 6392417 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 7509614 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 1108159 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 1112543 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.5987. Min Act: -0.1700
Data Index: 7154566 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 4192257 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6612. Min Act: -0.1700
Data Index: 2881385 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0049. Min Range: -7.0049
Max Act: 6.6299. Min Act: -0.1700
Data Index: 6392416 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19