Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1338. Min Range: -6.1338
Max Act: 6.1338. Min Act: -0.1700
Data Index: 6062156 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.9776. Min Act: -0.1700
Data Index: 3182772 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7901. Min Act: -0.1700
Data Index: 4503074 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.8213. Min Act: -0.1700
Data Index: 5041535 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7588. Min Act: -0.1700
Data Index: 938022 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7901. Min Act: -0.1700
Data Index: 1528587 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7276. Min Act: -0.1700
Data Index: 7850933 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7588. Min Act: -0.1700
Data Index: 3846920 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7276. Min Act: -0.1700
Data Index: 3980760 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7276. Min Act: -0.1700
Data Index: 1461763 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7276. Min Act: -0.1700
Data Index: 3763713 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7276. Min Act: -0.1700
Data Index: 1388239 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.7588. Min Act: -0.1700
Data Index: 17959 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.6651. Min Act: -0.1700
Data Index: 1652368 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.6963. Min Act: -0.1700
Data Index: 2875173 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.6338. Min Act: -0.1700
Data Index: 6129916 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.6651. Min Act: -0.1700
Data Index: 3516293 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.6338. Min Act: -0.1700
Data Index: 7828380 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.6338. Min Act: -0.1700
Data Index: 3387665 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1338. Min Range: -6.1338
Max Act: 5.6651. Min Act: -0.1700
Data Index: 5400729 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19