Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.4546. Min Act: -0.1700
Data Index: 4520991 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.4234. Min Act: -0.1700
Data Index: 3880926 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.3921. Min Act: -0.1700
Data Index: 1580660 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.3921. Min Act: -0.1700
Data Index: 1618906 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.3609. Min Act: -0.1700
Data Index: 5489298 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.3296. Min Act: -0.1700
Data Index: 7657899 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.2671. Min Act: -0.1700
Data Index: 2708539 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.2046. Min Act: -0.1700
Data Index: 6573523 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.1734. Min Act: -0.1700
Data Index: 8382017 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.1734. Min Act: -0.1700
Data Index: 5991130 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.1734. Min Act: -0.1700
Data Index: 3791584 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.1421. Min Act: -0.1700
Data Index: 6295037 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.1109. Min Act: -0.1700
Data Index: 1824694 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.0484. Min Act: -0.1700
Data Index: 6796525 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.0484. Min Act: -0.1700
Data Index: 5549325 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.0484. Min Act: -0.1700
Data Index: 3585111 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.0484. Min Act: -0.1700
Data Index: 1848858 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4546. Min Range: -6.4546
Max Act: 6.0171. Min Act: -0.1700
Data Index: 922913 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4546. Min Range: -6.4546
Max Act: 5.9859. Min Act: -0.1700
Data Index: 2620114 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4546. Min Range: -6.4546
Max Act: 5.9859. Min Act: -0.1700
Data Index: 2945682 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19