Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.9021. Min Act: -0.1700
Data Index: 2819637 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.8396. Min Act: -0.1700
Data Index: 7116541 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.8083. Min Act: -0.1700
Data Index: 4843429 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.8083. Min Act: -0.1700
Data Index: 2480020 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.7771. Min Act: -0.1700
Data Index: 888779 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.7771. Min Act: -0.1700
Data Index: 6982004 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.7458. Min Act: -0.1700
Data Index: 1142657 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.7458. Min Act: -0.1700
Data Index: 4178095 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.7458. Min Act: -0.1700
Data Index: 4826303 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6833. Min Act: -0.1700
Data Index: 6662403 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6521. Min Act: -0.1700
Data Index: 50892 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.7146. Min Act: -0.1700
Data Index: 6750100 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6833. Min Act: -0.1700
Data Index: 5600529 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6521. Min Act: -0.1700
Data Index: 1406789 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6521. Min Act: -0.1700
Data Index: 465022 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6521. Min Act: -0.1700
Data Index: 8157483 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.5896. Min Act: -0.1700
Data Index: 4926891 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6208. Min Act: -0.1700
Data Index: 6980676 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6208. Min Act: -0.1700
Data Index: 5645541 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9021. Min Range: -4.9021
Max Act: 4.6521. Min Act: -0.1700
Data Index: 4710712 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19