Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 352 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.6071. Min Act: -0.1700
Data Index: 6116639 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.6384. Min Act: -0.1700
Data Index: 7317801 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4821. Min Act: -0.1700
Data Index: 5639250 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.5134. Min Act: -0.1700
Data Index: 1495106 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.5134. Min Act: -0.1700
Data Index: 4754494 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4821. Min Act: -0.1700
Data Index: 3310426 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4821. Min Act: -0.1700
Data Index: 4968929 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4821. Min Act: -0.1700
Data Index: 2752380 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4509. Min Act: -0.1700
Data Index: 8049029 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4196. Min Act: -0.1700
Data Index: 5457322 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4196. Min Act: -0.1700
Data Index: 7318057 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4196. Min Act: -0.1700
Data Index: 1534249 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4509. Min Act: -0.1700
Data Index: 1660119 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.3884. Min Act: -0.1700
Data Index: 6818927 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.4196. Min Act: -0.1700
Data Index: 5778255 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.3571. Min Act: -0.1700
Data Index: 1985406 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2338610 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.3884. Min Act: -0.1700
Data Index: 5166235 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.3884. Min Act: -0.1700
Data Index: 4103947 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6384. Min Range: -5.6384
Max Act: 5.3259. Min Act: -0.1700
Data Index: 1153900 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19