Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0045. Min Range: -4.0045
Max Act: 4.0045. Min Act: -0.1700
Data Index: 6000694 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.9420. Min Act: -0.1700
Data Index: 6810858 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.9420. Min Act: -0.1700
Data Index: 2013428 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.8482. Min Act: -0.1700
Data Index: 2377301 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.8170. Min Act: -0.1700
Data Index: 2267931 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7857. Min Act: -0.1700
Data Index: 8596193 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7857. Min Act: -0.1700
Data Index: 7803008 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7700. Min Act: -0.1700
Data Index: 6460271 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.8013. Min Act: -0.1700
Data Index: 7920895 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7544. Min Act: -0.1700
Data Index: 5921084 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7544. Min Act: -0.1700
Data Index: 8236139 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7388. Min Act: -0.1700
Data Index: 3576248 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7544. Min Act: -0.1700
Data Index: 8747587 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7388. Min Act: -0.1700
Data Index: 1750065 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7075. Min Act: -0.1700
Data Index: 88217 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.6918. Min Act: -0.1700
Data Index: 6875080 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.6762. Min Act: -0.1700
Data Index: 1613801 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.7075. Min Act: -0.1700
Data Index: 885876 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.6762. Min Act: -0.1700
Data Index: 1684151 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0045. Min Range: -4.0045
Max Act: 3.6762. Min Act: -0.1700
Data Index: 8256622 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19