Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4553. Min Range: -9.4553
Max Act: 9.4553. Min Act: -0.1700
Data Index: 3366640 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4553. Min Range: -9.4553
Max Act: 8.6428. Min Act: -0.1700
Data Index: 671443 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4553. Min Range: -9.4553
Max Act: 8.5803. Min Act: -0.1700
Data Index: 4142548 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4553. Min Range: -9.4553
Max Act: 8.0803. Min Act: -0.1700
Data Index: 3910723 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4553. Min Range: -9.4553
Max Act: 8.0178. Min Act: -0.1700
Data Index: 7301734 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4553. Min Range: -9.4553
Max Act: 8.0178. Min Act: -0.1700
Data Index: 3921834 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.9866. Min Act: -0.1700
Data Index: 2329030 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.9866. Min Act: -0.1700
Data Index: 218467 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.9553. Min Act: -0.1700
Data Index: 3366639 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.9553. Min Act: -0.1700
Data Index: 5300799 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.9241. Min Act: -0.1700
Data Index: 4779890 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.9241. Min Act: -0.1700
Data Index: 1404263 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.8303. Min Act: -0.1700
Data Index: 8590451 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.7991. Min Act: -0.1700
Data Index: 5652902 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.7991. Min Act: -0.1700
Data Index: 1830491 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.7366. Min Act: -0.1700
Data Index: 3572844 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.7053. Min Act: -0.1700
Data Index: 1860130 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.7366. Min Act: -0.1700
Data Index: 7457063 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.7366. Min Act: -0.1700
Data Index: 6896538 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4553. Min Range: -9.4553
Max Act: 7.7053. Min Act: -0.1700
Data Index: 1497482 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19