Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.2572. Min Act: -0.1700
Data Index: 6701830 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.2884. Min Act: -0.1700
Data Index: 6957979 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.1634. Min Act: -0.1700
Data Index: 4592628 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.1634. Min Act: -0.1700
Data Index: 4581906 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.0384. Min Act: -0.1700
Data Index: 3700150 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.0697. Min Act: -0.1700
Data Index: 8576993 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.0697. Min Act: -0.1700
Data Index: 2206813 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.0697. Min Act: -0.1700
Data Index: 4699570 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.1009. Min Act: -0.1700
Data Index: 841507 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2884. Min Range: -6.2884
Max Act: 6.0072. Min Act: -0.1700
Data Index: 7018388 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.9447. Min Act: -0.1700
Data Index: 7365302 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.9134. Min Act: -0.1700
Data Index: 7230810 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.8822. Min Act: -0.1700
Data Index: 3539599 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.8822. Min Act: -0.1700
Data Index: 1657728 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.8822. Min Act: -0.1700
Data Index: 1357757 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.8197. Min Act: -0.1700
Data Index: 7908784 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.8197. Min Act: -0.1700
Data Index: 1016487 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.8197. Min Act: -0.1700
Data Index: 6419833 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.7884. Min Act: -0.1700
Data Index: 1989524 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2884. Min Range: -6.2884
Max Act: 5.7259. Min Act: -0.1700
Data Index: 7262812 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19