Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2585. Min Range: -5.2585
Max Act: 5.2585. Min Act: -0.1700
Data Index: 930164 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.9460. Min Act: -0.1700
Data Index: 8801121 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.9147. Min Act: -0.1700
Data Index: 2944233 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.8210. Min Act: -0.1700
Data Index: 8450249 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.7585. Min Act: -0.1700
Data Index: 5186272 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.7585. Min Act: -0.1700
Data Index: 3910866 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.7272. Min Act: -0.1700
Data Index: 6974298 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6960. Min Act: -0.1700
Data Index: 4485880 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6960. Min Act: -0.1700
Data Index: 798967 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6960. Min Act: -0.1700
Data Index: 5489669 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6647. Min Act: -0.1700
Data Index: 1188895 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6335. Min Act: -0.1700
Data Index: 6260774 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6335. Min Act: -0.1700
Data Index: 4484252 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6335. Min Act: -0.1700
Data Index: 8003109 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6022. Min Act: -0.1700
Data Index: 5434244 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6335. Min Act: -0.1700
Data Index: 2711105 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6022. Min Act: -0.1700
Data Index: 2252106 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.5710. Min Act: -0.1700
Data Index: 6850488 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.6022. Min Act: -0.1700
Data Index: 1062759 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2585. Min Range: -5.2585
Max Act: 4.5710. Min Act: -0.1700
Data Index: 6933352 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19