Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.5694. Min Act: -0.1700
Data Index: 2591101 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.4441. Min Act: -0.1700
Data Index: 3381914 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.3971. Min Act: -0.1700
Data Index: 7288290 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.2873. Min Act: -0.1700
Data Index: 6176482 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.2401. Min Act: -0.1700
Data Index: 3562166 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.2244. Min Act: -0.1700
Data Index: 1015234 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.2244. Min Act: -0.1700
Data Index: 3141401 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.1772. Min Act: -0.1700
Data Index: 8014956 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.1458. Min Act: -0.1700
Data Index: 6715762 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.1458. Min Act: -0.1700
Data Index: 3734040 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.1143. Min Act: -0.1700
Data Index: 4031212 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.1143. Min Act: -0.1700
Data Index: 3795419 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.1143. Min Act: -0.1700
Data Index: 4187119 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.1143. Min Act: -0.1700
Data Index: 400468 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.0985. Min Act: -0.1700
Data Index: 530836 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.0827. Min Act: -0.1700
Data Index: 6396770 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.0827. Min Act: -0.1700
Data Index: 8354178 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.0985. Min Act: -0.1700
Data Index: 3420835 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.0670. Min Act: -0.1700
Data Index: 6127553 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5694. Min Range: -3.5694
Max Act: 3.0827. Min Act: -0.1700
Data Index: 4925370 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19