Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5073 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.1145. Min Act: -0.1700
Data Index: 833467 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1145. Min Range: -5.1145
Max Act: 5.0207. Min Act: -0.1700
Data Index: 135153 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9895. Min Act: -0.1700
Data Index: 2896823 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.9582. Min Act: -0.1700
Data Index: 8578846 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8645. Min Act: -0.1700
Data Index: 1906852 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8332. Min Act: -0.1700
Data Index: 1077613 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8020. Min Act: -0.1700
Data Index: 2909924 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.8020. Min Act: -0.1700
Data Index: 237237 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7707. Min Act: -0.1700
Data Index: 3123227 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7707. Min Act: -0.1700
Data Index: 4694426 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7707. Min Act: -0.1700
Data Index: 7951960 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7395. Min Act: -0.1700
Data Index: 8151459 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7395. Min Act: -0.1700
Data Index: 3174967 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7395. Min Act: -0.1700
Data Index: 5246285 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7395. Min Act: -0.1700
Data Index: 8011711 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.6770. Min Act: -0.1700
Data Index: 5216003 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7082. Min Act: -0.1700
Data Index: 1361735 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7082. Min Act: -0.1700
Data Index: 7026523 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7082. Min Act: -0.1700
Data Index: 3483158 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1145. Min Range: -5.1145
Max Act: 4.7082. Min Act: -0.1700
Data Index: 4113206 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19