Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.8224. Min Act: -0.1700
Data Index: 433529 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.8849. Min Act: -0.1700
Data Index: 5113857 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.6662. Min Act: -0.1700
Data Index: 589039 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.5724. Min Act: -0.1700
Data Index: 5559665 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.5412. Min Act: -0.1700
Data Index: 632781 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.6037. Min Act: -0.1700
Data Index: 44933 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.5412. Min Act: -0.1700
Data Index: 5721791 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.5099. Min Act: -0.1700
Data Index: 2022069 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.5099. Min Act: -0.1700
Data Index: 8185697 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.5099. Min Act: -0.1700
Data Index: 3468385 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.5099. Min Act: -0.1700
Data Index: 2132389 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.4474. Min Act: -0.1700
Data Index: 6744101 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.4787. Min Act: -0.1700
Data Index: 2265680 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.4162. Min Act: -0.1700
Data Index: 7681316 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.4162. Min Act: -0.1700
Data Index: 7423827 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.4162. Min Act: -0.1700
Data Index: 751186 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.3849. Min Act: -0.1700
Data Index: 4151881 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.4162. Min Act: -0.1700
Data Index: 4265013 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.4162. Min Act: -0.1700
Data Index: 640094 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8849. Min Range: -5.8849
Max Act: 5.3849. Min Act: -0.1700
Data Index: 5018006 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19