Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.2525. Min Act: -0.1700
Data Index: 8347594 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.2213. Min Act: -0.1700
Data Index: 6747102 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1588. Min Act: -0.1700
Data Index: 5871854 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 8518881 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 6915590 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0963. Min Act: -0.1700
Data Index: 6882314 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0963. Min Act: -0.1700
Data Index: 3836488 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0963. Min Act: -0.1700
Data Index: 7179757 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0338. Min Act: -0.1700
Data Index: 4495938 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0338. Min Act: -0.1700
Data Index: 8301909 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 7301935 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 4859259 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 1648123 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0338. Min Act: -0.1700
Data Index: 1714635 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 5769035 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 6524945 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 4404736 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 5583440 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9400. Min Act: -0.1700
Data Index: 3970197 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9400. Min Act: -0.1700
Data Index: 5283045 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19