Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1427 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4472. Min Range: -8.4472
Max Act: 8.4472. Min Act: -0.1700
Data Index: 5697270 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4472. Min Range: -8.4472
Max Act: 8.1347. Min Act: -0.1700
Data Index: 4780480 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.9159. Min Act: -0.1700
Data Index: 6095650 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.8222. Min Act: -0.1700
Data Index: 1297689 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.7597. Min Act: -0.1700
Data Index: 1956005 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.7597. Min Act: -0.1700
Data Index: 3608664 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.7284. Min Act: -0.1700
Data Index: 7993275 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.6659. Min Act: -0.1700
Data Index: 5042028 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.6347. Min Act: -0.1700
Data Index: 5145434 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.6347. Min Act: -0.1700
Data Index: 7169546 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.6659. Min Act: -0.1700
Data Index: 4578425 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.6034. Min Act: -0.1700
Data Index: 5828477 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.5722. Min Act: -0.1700
Data Index: 7646291 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.5409. Min Act: -0.1700
Data Index: 6683570 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.4784. Min Act: -0.1700
Data Index: 3946406 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.4784. Min Act: -0.1700
Data Index: 7457582 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.4472. Min Act: -0.1700
Data Index: 1424120 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.4784. Min Act: -0.1700
Data Index: 2317288 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.4784. Min Act: -0.1700
Data Index: 1769805 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4472. Min Range: -8.4472
Max Act: 7.4784. Min Act: -0.1700
Data Index: 8785187 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19