Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0728. Min Range: -4.0728
Max Act: 4.0728. Min Act: -0.1700
Data Index: 4067198 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0728. Min Range: -4.0728
Max Act: 4.0103. Min Act: -0.1700
Data Index: 4290701 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9791. Min Act: -0.1700
Data Index: 5006067 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9791. Min Act: -0.1700
Data Index: 7190349 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9791. Min Act: -0.1700
Data Index: 4407953 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9791. Min Act: -0.1700
Data Index: 5619363 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9791. Min Act: -0.1700
Data Index: 379499 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9478. Min Act: -0.1700
Data Index: 2976061 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9478. Min Act: -0.1700
Data Index: 155040 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9165. Min Act: -0.1700
Data Index: 4290702 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9165. Min Act: -0.1700
Data Index: 1035415 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9165. Min Act: -0.1700
Data Index: 4290697 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9478. Min Act: -0.1700
Data Index: 6242342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9791. Min Act: -0.1700
Data Index: 6817271 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9478. Min Act: -0.1700
Data Index: 3263086 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9478. Min Act: -0.1700
Data Index: 4275891 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9791. Min Act: -0.1700
Data Index: 5280913 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9165. Min Act: -0.1700
Data Index: 7633141 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9478. Min Act: -0.1700
Data Index: 7912434 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0728. Min Range: -4.0728
Max Act: 3.9165. Min Act: -0.1700
Data Index: 8387271 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19