Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4936 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2051. Min Range: -6.2051
Max Act: 6.2051. Min Act: -0.1700
Data Index: 2077588 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2051. Min Range: -6.2051
Max Act: 6.1114. Min Act: -0.1700
Data Index: 1732293 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2051. Min Range: -6.2051
Max Act: 6.1114. Min Act: -0.1700
Data Index: 7827804 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2051. Min Range: -6.2051
Max Act: 6.0176. Min Act: -0.1700
Data Index: 1732283 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.9864. Min Act: -0.1700
Data Index: 1289619 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.9551. Min Act: -0.1700
Data Index: 6085112 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.9239. Min Act: -0.1700
Data Index: 3192043 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.9239. Min Act: -0.1700
Data Index: 7456671 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.9239. Min Act: -0.1700
Data Index: 6019282 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8926. Min Act: -0.1700
Data Index: 2295075 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8926. Min Act: -0.1700
Data Index: 2459244 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1929018 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8301. Min Act: -0.1700
Data Index: 3246369 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8614. Min Act: -0.1700
Data Index: 5217071 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8614. Min Act: -0.1700
Data Index: 2251556 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8301. Min Act: -0.1700
Data Index: 4300749 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8301. Min Act: -0.1700
Data Index: 2332083 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8301. Min Act: -0.1700
Data Index: 1289622 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.8301. Min Act: -0.1700
Data Index: 2332079 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2051. Min Range: -6.2051
Max Act: 5.7676. Min Act: -0.1700
Data Index: 6085110 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19