Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4559. Min Range: -6.4559
Max Act: 6.4559. Min Act: -0.1700
Data Index: 8006678 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4559. Min Range: -6.4559
Max Act: 6.1747. Min Act: -0.1700
Data Index: 8706508 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4559. Min Range: -6.4559
Max Act: 6.0497. Min Act: -0.1700
Data Index: 6467859 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4559. Min Range: -6.4559
Max Act: 6.0184. Min Act: -0.1700
Data Index: 4767972 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4559. Min Range: -6.4559
Max Act: 6.0184. Min Act: -0.1700
Data Index: 1101839 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4559. Min Range: -6.4559
Max Act: 6.0184. Min Act: -0.1700
Data Index: 1428879 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.9559. Min Act: -0.1700
Data Index: 7077524 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4040942 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.9247. Min Act: -0.1700
Data Index: 3368128 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.8934. Min Act: -0.1700
Data Index: 8535913 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.9559. Min Act: -0.1700
Data Index: 6191009 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.8622. Min Act: -0.1700
Data Index: 4078 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.8622. Min Act: -0.1700
Data Index: 2987447 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.8622. Min Act: -0.1700
Data Index: 1480744 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.7997. Min Act: -0.1700
Data Index: 6206946 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.7997. Min Act: -0.1700
Data Index: 6725817 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.7684. Min Act: -0.1700
Data Index: 4590988 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.7684. Min Act: -0.1700
Data Index: 1261041 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.7059. Min Act: -0.1700
Data Index: 592524 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4559. Min Range: -6.4559
Max Act: 5.7372. Min Act: -0.1700
Data Index: 3942148 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19