Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3124 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.4784. Min Act: -0.1700
Data Index: 7963273 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.4159. Min Act: -0.1700
Data Index: 3188653 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.3847. Min Act: -0.1700
Data Index: 4868598 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.1972. Min Act: -0.1700
Data Index: 4678429 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.1659. Min Act: -0.1700
Data Index: 6720343 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.1034. Min Act: -0.1700
Data Index: 6720341 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.0409. Min Act: -0.1700
Data Index: 4406565 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.0722. Min Act: -0.1700
Data Index: 4896182 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.0097. Min Act: -0.1700
Data Index: 2403711 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4784. Min Range: -5.4784
Max Act: 5.0097. Min Act: -0.1700
Data Index: 5870146 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.9472. Min Act: -0.1700
Data Index: 7851268 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.9784. Min Act: -0.1700
Data Index: 2275865 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.9472. Min Act: -0.1700
Data Index: 4402642 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.9159. Min Act: -0.1700
Data Index: 7662583 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.9159. Min Act: -0.1700
Data Index: 2659073 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.8847. Min Act: -0.1700
Data Index: 8659765 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.8847. Min Act: -0.1700
Data Index: 5341269 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.8534. Min Act: -0.1700
Data Index: 4805506 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.8534. Min Act: -0.1700
Data Index: 294959 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4784. Min Range: -5.4784
Max Act: 4.8534. Min Act: -0.1700
Data Index: 2659072 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19