Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.8888. Min Act: -0.1700
Data Index: 7467769 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.8263. Min Act: -0.1700
Data Index: 6199020 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.7638. Min Act: -0.1700
Data Index: 5131642 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.6075. Min Act: -0.1700
Data Index: 3236697 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.5450. Min Act: -0.1700
Data Index: 2571474 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.3888. Min Act: -0.1700
Data Index: 492635 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.3575. Min Act: -0.1700
Data Index: 1565383 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2950. Min Act: -0.1700
Data Index: 3584635 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2950. Min Act: -0.1700
Data Index: 1331101 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2638. Min Act: -0.1700
Data Index: 3448958 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2638. Min Act: -0.1700
Data Index: 3033796 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2638. Min Act: -0.1700
Data Index: 2483109 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2325. Min Act: -0.1700
Data Index: 4284496 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2325. Min Act: -0.1700
Data Index: 8571953 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2013. Min Act: -0.1700
Data Index: 7654776 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2325. Min Act: -0.1700
Data Index: 6904738 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2013. Min Act: -0.1700
Data Index: 5079261 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2013. Min Act: -0.1700
Data Index: 1990367 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.2013. Min Act: -0.1700
Data Index: 560303 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8888. Min Range: -7.8888
Max Act: 7.1075. Min Act: -0.1700
Data Index: 577056 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19