Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.2018. Min Act: -0.1700
Data Index: 5290391 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.1393. Min Act: -0.1700
Data Index: 2788441 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.1393. Min Act: -0.1700
Data Index: 6354305 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.1393. Min Act: -0.1700
Data Index: 5941374 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.1393. Min Act: -0.1700
Data Index: 741347 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.1080. Min Act: -0.1700
Data Index: 6157327 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0455. Min Act: -0.1700
Data Index: 5183247 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0768. Min Act: -0.1700
Data Index: 6173746 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0455. Min Act: -0.1700
Data Index: 3460269 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0455. Min Act: -0.1700
Data Index: 762226 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0143. Min Act: -0.1700
Data Index: 4921115 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0143. Min Act: -0.1700
Data Index: 1605804 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0143. Min Act: -0.1700
Data Index: 8204841 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.9830. Min Act: -0.1700
Data Index: 6707752 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0143. Min Act: -0.1700
Data Index: 5265494 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0143. Min Act: -0.1700
Data Index: 5100864 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.9518. Min Act: -0.1700
Data Index: 2210449 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.9518. Min Act: -0.1700
Data Index: 2078616 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0143. Min Act: -0.1700
Data Index: 8297459 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.9830. Min Act: -0.1700
Data Index: 6497136 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19