Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4165. Min Range: -6.4165
Max Act: 6.4165. Min Act: -0.1700
Data Index: 2719063 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4165. Min Range: -6.4165
Max Act: 6.1040. Min Act: -0.1700
Data Index: 7745469 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4165. Min Range: -6.4165
Max Act: 6.0728. Min Act: -0.1700
Data Index: 7117565 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4165. Min Range: -6.4165
Max Act: 6.1040. Min Act: -0.1700
Data Index: 6681062 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4165. Min Range: -6.4165
Max Act: 6.0415. Min Act: -0.1700
Data Index: 5224075 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4165. Min Range: -6.4165
Max Act: 6.0103. Min Act: -0.1700
Data Index: 6600638 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.9478. Min Act: -0.1700
Data Index: 5726446 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4165. Min Range: -6.4165
Max Act: 6.0103. Min Act: -0.1700
Data Index: 6612286 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.9478. Min Act: -0.1700
Data Index: 4652649 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.9478. Min Act: -0.1700
Data Index: 824993 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.8853. Min Act: -0.1700
Data Index: 7059905 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.9165. Min Act: -0.1700
Data Index: 2719062 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.8228. Min Act: -0.1700
Data Index: 1407926 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.8540. Min Act: -0.1700
Data Index: 6127389 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.8540. Min Act: -0.1700
Data Index: 8332744 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.8540. Min Act: -0.1700
Data Index: 2028976 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.8228. Min Act: -0.1700
Data Index: 2638390 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.8228. Min Act: -0.1700
Data Index: 5850928 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.7915. Min Act: -0.1700
Data Index: 3745740 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4165. Min Range: -6.4165
Max Act: 5.7603. Min Act: -0.1700
Data Index: 1172269 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19