Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.4133. Min Act: -0.1700
Data Index: 8442658 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.3508. Min Act: -0.1700
Data Index: 8066343 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.3508. Min Act: -0.1700
Data Index: 2021367 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.3196. Min Act: -0.1700
Data Index: 6827188 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.2571. Min Act: -0.1700
Data Index: 3195736 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.1946. Min Act: -0.1700
Data Index: 969298 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.1946. Min Act: -0.1700
Data Index: 8162242 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.1633. Min Act: -0.1700
Data Index: 6282130 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.1321. Min Act: -0.1700
Data Index: 1124027 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.1008. Min Act: -0.1700
Data Index: 7027579 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.1321. Min Act: -0.1700
Data Index: 2511184 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0696. Min Act: -0.1700
Data Index: 4139329 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0696. Min Act: -0.1700
Data Index: 3053524 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0696. Min Act: -0.1700
Data Index: 8231096 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0696. Min Act: -0.1700
Data Index: 6519689 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0696. Min Act: -0.1700
Data Index: 6333754 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0071. Min Act: -0.1700
Data Index: 5751977 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0071. Min Act: -0.1700
Data Index: 4720478 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0383. Min Act: -0.1700
Data Index: 7608033 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4133. Min Range: -5.4133
Max Act: 5.0071. Min Act: -0.1700
Data Index: 673011 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19