Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.8079. Min Act: -0.1700
Data Index: 1768727 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.4637. Min Act: -0.1700
Data Index: 1945379 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.4323. Min Act: -0.1700
Data Index: 4767353 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.4010. Min Act: -0.1700
Data Index: 118966 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.4166. Min Act: -0.1700
Data Index: 4420 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.3696. Min Act: -0.1700
Data Index: 2824170 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.3539. Min Act: -0.1700
Data Index: 4185338 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.3068. Min Act: -0.1700
Data Index: 365647 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.2754. Min Act: -0.1700
Data Index: 7423660 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.2597. Min Act: -0.1700
Data Index: 6560171 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.2440. Min Act: -0.1700
Data Index: 4197714 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.2126. Min Act: -0.1700
Data Index: 1492657 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.2126. Min Act: -0.1700
Data Index: 6800970 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.1969. Min Act: -0.1700
Data Index: 6511405 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.1969. Min Act: -0.1700
Data Index: 2108583 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.1969. Min Act: -0.1700
Data Index: 4993202 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.1811. Min Act: -0.1700
Data Index: 4287130 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.1811. Min Act: -0.1700
Data Index: 5441029 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.1811. Min Act: -0.1700
Data Index: 2319750 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8079. Min Range: -3.8079
Max Act: 3.1654. Min Act: -0.1700
Data Index: 4403887 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19