Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.7083. Min Act: -0.1700
Data Index: 1788735 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3333. Min Act: -0.1700
Data Index: 5018719 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3020. Min Act: -0.1700
Data Index: 2978699 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2708. Min Act: -0.1700
Data Index: 2294824 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1770. Min Act: -0.1700
Data Index: 3611623 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1458. Min Act: -0.1700
Data Index: 1930747 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1770. Min Act: -0.1700
Data Index: 5599897 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1770. Min Act: -0.1700
Data Index: 8321785 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1145. Min Act: -0.1700
Data Index: 1263119 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1145. Min Act: -0.1700
Data Index: 7747635 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0833. Min Act: -0.1700
Data Index: 1884440 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0833. Min Act: -0.1700
Data Index: 2101184 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0520. Min Act: -0.1700
Data Index: 981040 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0520. Min Act: -0.1700
Data Index: 1614797 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0520. Min Act: -0.1700
Data Index: 1253271 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0520. Min Act: -0.1700
Data Index: 6583741 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0208. Min Act: -0.1700
Data Index: 1909328 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0208. Min Act: -0.1700
Data Index: 6393675 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0208. Min Act: -0.1700
Data Index: 2093859 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.0208. Min Act: -0.1700
Data Index: 3914254 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19