Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1383. Min Range: -5.1383
Max Act: 5.1383. Min Act: -0.1700
Data Index: 2007451 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1383. Min Range: -5.1383
Max Act: 5.0446. Min Act: -0.1700
Data Index: 2170393 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1383. Min Range: -5.1383
Max Act: 5.0133. Min Act: -0.1700
Data Index: 905173 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9508. Min Act: -0.1700
Data Index: 1678647 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9821. Min Act: -0.1700
Data Index: 2616144 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9508. Min Act: -0.1700
Data Index: 5264264 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9196. Min Act: -0.1700
Data Index: 7237797 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9196. Min Act: -0.1700
Data Index: 6994017 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9196. Min Act: -0.1700
Data Index: 5788922 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9196. Min Act: -0.1700
Data Index: 6976847 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8883. Min Act: -0.1700
Data Index: 2493197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8883. Min Act: -0.1700
Data Index: 7884790 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8883. Min Act: -0.1700
Data Index: 2709629 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.9196. Min Act: -0.1700
Data Index: 3176093 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8571. Min Act: -0.1700
Data Index: 1802155 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8571. Min Act: -0.1700
Data Index: 3994506 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8571. Min Act: -0.1700
Data Index: 4405400 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8571. Min Act: -0.1700
Data Index: 7004487 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.7946. Min Act: -0.1700
Data Index: 1885812 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1383. Min Range: -5.1383
Max Act: 4.8258. Min Act: -0.1700
Data Index: 6572772 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19