Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1296 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2814. Min Range: -7.2814
Max Act: 7.2814. Min Act: -0.1700
Data Index: 354641 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.9064. Min Act: -0.1700
Data Index: 5911024 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.8439. Min Act: -0.1700
Data Index: 5611169 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.8439. Min Act: -0.1700
Data Index: 7446869 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.8439. Min Act: -0.1700
Data Index: 5680351 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.7502. Min Act: -0.1700
Data Index: 4751828 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.7189. Min Act: -0.1700
Data Index: 6994875 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.7189. Min Act: -0.1700
Data Index: 4167150 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.6564. Min Act: -0.1700
Data Index: 2010098 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.6564. Min Act: -0.1700
Data Index: 7414590 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.6252. Min Act: -0.1700
Data Index: 7886352 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5627. Min Act: -0.1700
Data Index: 8382430 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5939. Min Act: -0.1700
Data Index: 325216 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.6252. Min Act: -0.1700
Data Index: 1137783 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5627. Min Act: -0.1700
Data Index: 1971774 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5627. Min Act: -0.1700
Data Index: 2253113 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5627. Min Act: -0.1700
Data Index: 7621498 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5314. Min Act: -0.1700
Data Index: 7642744 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5002. Min Act: -0.1700
Data Index: 3547173 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2814. Min Range: -7.2814
Max Act: 6.5314. Min Act: -0.1700
Data Index: 5611167 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19