Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.2133. Min Act: -0.1700
Data Index: 5181094 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.1818. Min Act: -0.1700
Data Index: 455611 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.1346. Min Act: -0.1700
Data Index: 5299790 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.0084. Min Act: -0.1700
Data Index: 5773536 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2133. Min Range: -3.2133
Max Act: 3.0242. Min Act: -0.1700
Data Index: 921765 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9768. Min Act: -0.1700
Data Index: 120507 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9452. Min Act: -0.1700
Data Index: 748624 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9610. Min Act: -0.1700
Data Index: 6213717 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9293. Min Act: -0.1700
Data Index: 3939836 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9293. Min Act: -0.1700
Data Index: 755315 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8976. Min Act: -0.1700
Data Index: 115490 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9293. Min Act: -0.1700
Data Index: 4318745 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8818. Min Act: -0.1700
Data Index: 8684011 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.9135. Min Act: -0.1700
Data Index: 2533860 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8659. Min Act: -0.1700
Data Index: 8383403 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8818. Min Act: -0.1700
Data Index: 7621845 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8500. Min Act: -0.1700
Data Index: 5975218 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8500. Min Act: -0.1700
Data Index: 6888530 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8500. Min Act: -0.1700
Data Index: 2965040 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2133. Min Range: -3.2133
Max Act: 2.8341. Min Act: -0.1700
Data Index: 4290497 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19