Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 436 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.0657. Min Range: -4.0657
Max Act: 4.0032. Min Act: -0.1700
Data Index: 3548804 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0657. Min Range: -4.0657
Max Act: 4.0657. Min Act: -0.1700
Data Index: 5737899 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0657. Min Range: -4.0657
Max Act: 4.0032. Min Act: -0.1700
Data Index: 4263363 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9719. Min Act: -0.1700
Data Index: 6788957 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9719. Min Act: -0.1700
Data Index: 3109360 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9407. Min Act: -0.1700
Data Index: 3911947 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9719. Min Act: -0.1700
Data Index: 3669154 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0657. Min Range: -4.0657
Max Act: 4.0032. Min Act: -0.1700
Data Index: 5815499 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9407. Min Act: -0.1700
Data Index: 6287150 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9407. Min Act: -0.1700
Data Index: 5357328 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9094. Min Act: -0.1700
Data Index: 968257 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9407. Min Act: -0.1700
Data Index: 862315 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9094. Min Act: -0.1700
Data Index: 8812133 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9094. Min Act: -0.1700
Data Index: 5017302 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.8781. Min Act: -0.1700
Data Index: 2804653 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9094. Min Act: -0.1700
Data Index: 8017419 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9094. Min Act: -0.1700
Data Index: 3346818 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9094. Min Act: -0.1700
Data Index: 1954701 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.8781. Min Act: -0.1700
Data Index: 4106421 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0657. Min Range: -4.0657
Max Act: 3.9094. Min Act: -0.1700
Data Index: 5734848 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19