Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5592 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2065. Min Range: -5.2065
Max Act: 5.1752. Min Act: -0.1700
Data Index: 1279018 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2065. Min Range: -5.2065
Max Act: 5.2065. Min Act: -0.1700
Data Index: 4392031 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2065. Min Range: -5.2065
Max Act: 5.1752. Min Act: -0.1700
Data Index: 4641421 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2065. Min Range: -5.2065
Max Act: 5.1440. Min Act: -0.1700
Data Index: 6806148 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2065. Min Range: -5.2065
Max Act: 5.0190. Min Act: -0.1700
Data Index: 950873 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2065. Min Range: -5.2065
Max Act: 5.0190. Min Act: -0.1700
Data Index: 5116081 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.9252. Min Act: -0.1700
Data Index: 8204276 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.9252. Min Act: -0.1700
Data Index: 4139870 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8940. Min Act: -0.1700
Data Index: 6597088 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8940. Min Act: -0.1700
Data Index: 2677441 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8940. Min Act: -0.1699
Data Index: 973907 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8940. Min Act: -0.1700
Data Index: 5180280 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8627. Min Act: -0.1700
Data Index: 4392032 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8627. Min Act: -0.1700
Data Index: 7748520 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8627. Min Act: -0.1700
Data Index: 160617 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8315. Min Act: -0.1700
Data Index: 979578 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8315. Min Act: -0.1700
Data Index: 7074775 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8315. Min Act: -0.1700
Data Index: 8555376 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8627. Min Act: -0.1700
Data Index: 2677440 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2065. Min Range: -5.2065
Max Act: 4.8002. Min Act: -0.1700
Data Index: 6337102 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19