Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1481 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2049. Min Range: -4.2049
Max Act: 4.2049. Min Act: -0.1700
Data Index: 7856438 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2049. Min Range: -4.2049
Max Act: 4.2049. Min Act: -0.1700
Data Index: 6965131 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2049. Min Range: -4.2049
Max Act: 4.1112. Min Act: -0.1700
Data Index: 8350414 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2049. Min Range: -4.2049
Max Act: 4.1112. Min Act: -0.1700
Data Index: 6091068 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.9861. Min Act: -0.1700
Data Index: 6417514 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2049. Min Range: -4.2049
Max Act: 4.0174. Min Act: -0.1700
Data Index: 5562434 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2049. Min Range: -4.2049
Max Act: 4.0174. Min Act: -0.1700
Data Index: 4903876 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.9549. Min Act: -0.1700
Data Index: 3328168 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.9549. Min Act: -0.1700
Data Index: 5296184 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.9549. Min Act: -0.1700
Data Index: 3044087 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.9549. Min Act: -0.1700
Data Index: 533610 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.9236. Min Act: -0.1700
Data Index: 750106 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.8924. Min Act: -0.1700
Data Index: 6000039 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.8611. Min Act: -0.1700
Data Index: 5294435 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.8611. Min Act: -0.1700
Data Index: 5736967 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.8611. Min Act: -0.1700
Data Index: 7553587 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.8611. Min Act: -0.1700
Data Index: 7540905 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.8611. Min Act: -0.1700
Data Index: 6406771 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.8298. Min Act: -0.1700
Data Index: 6096654 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2049. Min Range: -4.2049
Max Act: 3.7985. Min Act: -0.1700
Data Index: 2097573 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19