Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.7104. Min Act: -0.1700
Data Index: 884685 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.5539. Min Act: -0.1700
Data Index: 8560753 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.5226. Min Act: -0.1700
Data Index: 6555639 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.5069. Min Act: -0.1700
Data Index: 5898344 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.4913. Min Act: -0.1700
Data Index: 2843032 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.4756. Min Act: -0.1700
Data Index: 4713935 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.4286. Min Act: -0.1700
Data Index: 1160250 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.4129. Min Act: -0.1700
Data Index: 1218856 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.4129. Min Act: -0.1700
Data Index: 6533566 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3973. Min Act: -0.1700
Data Index: 8297493 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.4129. Min Act: -0.1700
Data Index: 39907 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3973. Min Act: -0.1700
Data Index: 152871 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3816. Min Act: -0.1700
Data Index: 4799140 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3816. Min Act: -0.1700
Data Index: 1907972 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3659. Min Act: -0.1700
Data Index: 1162716 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3659. Min Act: -0.1700
Data Index: 2092289 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3659. Min Act: -0.1700
Data Index: 3370493 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3659. Min Act: -0.1700
Data Index: 710378 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3659. Min Act: -0.1700
Data Index: 6253975 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7104. Min Range: -3.7104
Max Act: 3.3502. Min Act: -0.1700
Data Index: 6672369 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19