Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.9684. Min Act: -0.1700
Data Index: 6092112 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.9059. Min Act: -0.1700
Data Index: 6670502 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.8121. Min Act: -0.1700
Data Index: 8164928 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.8277. Min Act: -0.1700
Data Index: 7454105 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7964. Min Act: -0.1700
Data Index: 6868018 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7964. Min Act: -0.1700
Data Index: 4819843 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.8121. Min Act: -0.1700
Data Index: 1061052 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7808. Min Act: -0.1700
Data Index: 7268322 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 2493828 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7964. Min Act: -0.1700
Data Index: 5047153 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7808. Min Act: -0.1700
Data Index: 6571135 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7652. Min Act: -0.1700
Data Index: 1528409 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7652. Min Act: -0.1700
Data Index: 4883354 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7339. Min Act: -0.1700
Data Index: 713313 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7339. Min Act: -0.1700
Data Index: 8584001 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 5880754 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 5558914 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7495. Min Act: -0.1700
Data Index: 8011024 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7339. Min Act: -0.1700
Data Index: 6902579 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9684. Min Range: -3.9684
Max Act: 3.7339. Min Act: -0.1700
Data Index: 1946101 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19