Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1068 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.9185. Min Act: -0.1700
Data Index: 7480453 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.8502. Min Act: -0.1700
Data Index: 4048366 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.8164. Min Act: -0.1700
Data Index: 1178172 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7996. Min Act: -0.1700
Data Index: 8537170 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.8164. Min Act: -0.1700
Data Index: 5181229 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7996. Min Act: -0.1700
Data Index: 7538978 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7913. Min Act: -0.1700
Data Index: 1581190 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7913. Min Act: -0.1700
Data Index: 1193670 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7829. Min Act: -0.1700
Data Index: 5377703 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7829. Min Act: -0.1700
Data Index: 8069079 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7913. Min Act: -0.1700
Data Index: 2411124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7746. Min Act: -0.1700
Data Index: 335133 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7662. Min Act: -0.1700
Data Index: 1545425 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7662. Min Act: -0.1700
Data Index: 8144187 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7662. Min Act: -0.1700
Data Index: 1695492 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7579. Min Act: -0.1700
Data Index: 3121061 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7579. Min Act: -0.1700
Data Index: 6824879 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7496. Min Act: -0.1700
Data Index: 4426126 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7496. Min Act: -0.1700
Data Index: 6811479 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9185. Min Range: -0.9185
Max Act: 0.7496. Min Act: -0.1700
Data Index: 348200 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19