Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.3609. Min Act: -0.1700
Data Index: 1129262 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 2995401 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 5471706 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.1734. Min Act: -0.1699
Data Index: 135711 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.1109. Min Act: -0.1700
Data Index: 8001966 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.0796. Min Act: -0.1700
Data Index: 4058883 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.0171. Min Act: -0.1700
Data Index: 7625841 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.9546. Min Act: -0.1700
Data Index: 2643097 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.9546. Min Act: -0.1700
Data Index: 6325207 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.9234. Min Act: -0.1700
Data Index: 8632200 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.9234. Min Act: -0.1700
Data Index: 8442473 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.8921. Min Act: -0.1700
Data Index: 3698081 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.8921. Min Act: -0.1700
Data Index: 5421058 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.8921. Min Act: -0.1700
Data Index: 1746644 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.8609. Min Act: -0.1700
Data Index: 8219636 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.8609. Min Act: -0.1700
Data Index: 5321664 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.8609. Min Act: -0.1700
Data Index: 6694521 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.7984. Min Act: -0.1700
Data Index: 6231694 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.8296. Min Act: -0.1700
Data Index: 4972741 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3609. Min Range: -6.3609
Max Act: 5.7984. Min Act: -0.1700
Data Index: 4134850 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19