Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2588 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0566. Min Range: -7.0566
Max Act: 7.0566. Min Act: -0.1700
Data Index: 724567 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.8379. Min Act: -0.1700
Data Index: 1993385 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.7129. Min Act: -0.1700
Data Index: 6598753 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.6191. Min Act: -0.1700
Data Index: 2951838 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5879. Min Act: -0.1700
Data Index: 8108151 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5879. Min Act: -0.1700
Data Index: 11965 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5566. Min Act: -0.1700
Data Index: 4874748 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5566. Min Act: -0.1700
Data Index: 590756 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5566. Min Act: -0.1700
Data Index: 2623580 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5254. Min Act: -0.1700
Data Index: 5802782 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5254. Min Act: -0.1700
Data Index: 7585784 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.5254. Min Act: -0.1700
Data Index: 8315720 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4941. Min Act: -0.1700
Data Index: 862789 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4941. Min Act: -0.1700
Data Index: 3956667 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4629. Min Act: -0.1700
Data Index: 3630872 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4629. Min Act: -0.1700
Data Index: 1335291 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4316. Min Act: -0.1700
Data Index: 2141733 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4316. Min Act: -0.1700
Data Index: 6151698 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4629. Min Act: -0.1700
Data Index: 1585107 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0566. Min Range: -7.0566
Max Act: 6.4004. Min Act: -0.1700
Data Index: 6545003 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19