Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1436 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.8710. Min Act: -0.1700
Data Index: 8595854 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.8398. Min Act: -0.1700
Data Index: 4938306 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.8398. Min Act: -0.1700
Data Index: 2338091 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7773. Min Act: -0.1700
Data Index: 2669039 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.8085. Min Act: -0.1700
Data Index: 8020180 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7460. Min Act: -0.1700
Data Index: 752290 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7460. Min Act: -0.1700
Data Index: 5878739 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7460. Min Act: -0.1700
Data Index: 5015821 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7773. Min Act: -0.1700
Data Index: 3313106 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7460. Min Act: -0.1700
Data Index: 420340 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7148. Min Act: -0.1700
Data Index: 2928224 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7148. Min Act: -0.1700
Data Index: 2776847 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7148. Min Act: -0.1700
Data Index: 4753727 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7148. Min Act: -0.1700
Data Index: 1472821 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7148. Min Act: -0.1700
Data Index: 175236 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.7148. Min Act: -0.1700
Data Index: 4315958 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.6835. Min Act: -0.1700
Data Index: 3349346 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.6835. Min Act: -0.1700
Data Index: 5896050 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.6835. Min Act: -0.1700
Data Index: 6100636 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8710. Min Range: -4.8710
Max Act: 4.6835. Min Act: -0.1700
Data Index: 7143010 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19