Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2343 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.8946. Min Act: -0.1700
Data Index: 4753472 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.4571. Min Act: -0.1700
Data Index: 4240925 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.2696. Min Act: -0.1700
Data Index: 7098257 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.2696. Min Act: -0.1700
Data Index: 8090120 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.2383. Min Act: -0.1700
Data Index: 8010461 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.2071. Min Act: -0.1700
Data Index: 3557167 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.1758. Min Act: -0.1700
Data Index: 149676 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.1446. Min Act: -0.1700
Data Index: 3753333 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.1446. Min Act: -0.1700
Data Index: 4714781 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.0508. Min Act: -0.1700
Data Index: 82621 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.0508. Min Act: -0.1700
Data Index: 7523989 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.0508. Min Act: -0.1700
Data Index: 7185655 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.0508. Min Act: -0.1700
Data Index: 2182564 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.0508. Min Act: -0.1700
Data Index: 4506779 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8946. Min Range: -6.8946
Max Act: 5.9883. Min Act: -0.1700
Data Index: 14693 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.0196. Min Act: -0.1700
Data Index: 3758340 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8946. Min Range: -6.8946
Max Act: 6.0508. Min Act: -0.1700
Data Index: 6440971 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8946. Min Range: -6.8946
Max Act: 5.9883. Min Act: -0.1700
Data Index: 8010471 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8946. Min Range: -6.8946
Max Act: 5.9883. Min Act: -0.1700
Data Index: 715254 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8946. Min Range: -6.8946
Max Act: 5.9883. Min Act: -0.1700
Data Index: 242185 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19