Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1094. Min Range: -5.1094
Max Act: 5.1094. Min Act: -0.1700
Data Index: 2510917 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7969. Min Act: -0.1700
Data Index: 6988860 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.8282. Min Act: -0.1700
Data Index: 6790404 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7969. Min Act: -0.1700
Data Index: 5697987 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7657. Min Act: -0.1700
Data Index: 4209983 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7032. Min Act: -0.1700
Data Index: 6409477 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7344. Min Act: -0.1700
Data Index: 720550 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7344. Min Act: -0.1700
Data Index: 6669295 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6719. Min Act: -0.1700
Data Index: 5935245 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7032. Min Act: -0.1700
Data Index: 2462420 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7032. Min Act: -0.1700
Data Index: 6342563 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7032. Min Act: -0.1700
Data Index: 7375496 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.7032. Min Act: -0.1700
Data Index: 8786221 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6719. Min Act: -0.1700
Data Index: 1442170 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6407. Min Act: -0.1700
Data Index: 5442759 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6407. Min Act: -0.1700
Data Index: 8118786 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6094. Min Act: -0.1700
Data Index: 4441482 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6094. Min Act: -0.1700
Data Index: 4103797 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6094. Min Act: -0.1700
Data Index: 6173491 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1094. Min Range: -5.1094
Max Act: 4.6094. Min Act: -0.1700
Data Index: 5207212 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19