Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1112 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7000. Min Range: -9.7000
Max Act: 9.7000. Min Act: -0.1700
Data Index: 7816457 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7000. Min Range: -9.7000
Max Act: 9.5750. Min Act: -0.1700
Data Index: 1329001 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7000. Min Range: -9.7000
Max Act: 9.5750. Min Act: -0.1700
Data Index: 8665928 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7000. Min Range: -9.7000
Max Act: 9.0750. Min Act: -0.1700
Data Index: 2603327 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.8875. Min Act: -0.1700
Data Index: 4608291 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.8875. Min Act: -0.1700
Data Index: 2603325 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.7625. Min Act: -0.1700
Data Index: 8078722 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.7625. Min Act: -0.1700
Data Index: 1925382 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.7625. Min Act: -0.1700
Data Index: 7095842 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.7000. Min Act: -0.1700
Data Index: 1793327 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.6375. Min Act: -0.1700
Data Index: 3352103 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.5125. Min Act: -0.1700
Data Index: 110923 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.5125. Min Act: -0.1700
Data Index: 2385634 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.4500. Min Act: -0.1700
Data Index: 5280536 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.3250. Min Act: -0.1699
Data Index: 2603320 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.3250. Min Act: -0.1700
Data Index: 1422082 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.3250. Min Act: -0.1700
Data Index: 8178890 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.2625. Min Act: -0.1700
Data Index: 136218 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.2625. Min Act: -0.1700
Data Index: 5634488 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7000. Min Range: -9.7000
Max Act: 8.2625. Min Act: -0.1700
Data Index: 3111472 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19