Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3714 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.2107. Min Act: -0.1700
Data Index: 4001433 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.2107. Min Act: -0.1700
Data Index: 6432112 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.1794. Min Act: -0.1700
Data Index: 770458 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.1482. Min Act: -0.1699
Data Index: 661431 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.1482. Min Act: -0.1700
Data Index: 1663178 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.1169. Min Act: -0.1700
Data Index: 4163029 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.1482. Min Act: -0.1700
Data Index: 3006759 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.1169. Min Act: -0.1700
Data Index: 7699336 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0857. Min Act: -0.1700
Data Index: 6384335 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0857. Min Act: -0.1700
Data Index: 2946108 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0544. Min Act: -0.1700
Data Index: 6165570 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0544. Min Act: -0.1700
Data Index: 2765134 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0544. Min Act: -0.1700
Data Index: 3343839 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0544. Min Act: -0.1700
Data Index: 6309634 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0544. Min Act: -0.1700
Data Index: 4350945 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0544. Min Act: -0.1700
Data Index: 6307836 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0232. Min Act: -0.1700
Data Index: 2935779 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0232. Min Act: -0.1700
Data Index: 5688088 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0232. Min Act: -0.1700
Data Index: 1657764 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2107. Min Range: -5.2107
Max Act: 5.0232. Min Act: -0.1700
Data Index: 359150 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19