Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0892. Min Range: -9.0892
Max Act: 9.0892. Min Act: -0.1700
Data Index: 7876856 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.9642. Min Act: -0.1700
Data Index: 6712150 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.9642. Min Act: -0.1700
Data Index: 1772843 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.8392. Min Act: -0.1700
Data Index: 6581647 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.9017. Min Act: -0.1700
Data Index: 6782082 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 1915219 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 8511212 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7142. Min Act: -0.1700
Data Index: 6410159 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 5468383 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 7273638 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 5252645 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 6712151 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7142. Min Act: -0.1700
Data Index: 6951057 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7142. Min Act: -0.1700
Data Index: 3699492 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 3646910 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7142. Min Act: -0.1700
Data Index: 6889424 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.6517. Min Act: -0.1700
Data Index: 8471680 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7142. Min Act: -0.1700
Data Index: 1271654 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7142. Min Act: -0.1700
Data Index: 7411244 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0892. Min Range: -9.0892
Max Act: 8.7767. Min Act: -0.1700
Data Index: 1674384 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19