Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.2135. Min Act: -0.1700
Data Index: 8239791 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.1978. Min Act: -0.1700
Data Index: 6949757 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.1191. Min Act: -0.1700
Data Index: 7966340 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.0560. Min Act: -0.1700
Data Index: 8628662 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.0560. Min Act: -0.1700
Data Index: 1884824 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.0087. Min Act: -0.1700
Data Index: 3511083 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.0402. Min Act: -0.1700
Data Index: 5193766 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2135. Min Range: -3.2135
Max Act: 3.0245. Min Act: -0.1700
Data Index: 6361810 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9929. Min Act: -0.1700
Data Index: 919090 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9929. Min Act: -0.1700
Data Index: 4868006 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9612. Min Act: -0.1700
Data Index: 6494869 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9612. Min Act: -0.1700
Data Index: 8209914 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9929. Min Act: -0.1700
Data Index: 1700916 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9770. Min Act: -0.1700
Data Index: 6475347 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9454. Min Act: -0.1700
Data Index: 7993209 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9454. Min Act: -0.1700
Data Index: 893091 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9612. Min Act: -0.1700
Data Index: 894947 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9612. Min Act: -0.1700
Data Index: 4874419 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9612. Min Act: -0.1700
Data Index: 2945875 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2135. Min Range: -3.2135
Max Act: 2.9612. Min Act: -0.1700
Data Index: 5755421 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19