Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.1599. Min Act: -0.1700
Data Index: 2830610 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.0974. Min Act: -0.1700
Data Index: 5037155 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.1287. Min Act: -0.1700
Data Index: 8101374 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.0662. Min Act: -0.1700
Data Index: 3113508 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.0349. Min Act: -0.1700
Data Index: 4565569 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1599. Min Range: -7.1599
Max Act: 7.0037. Min Act: -0.1700
Data Index: 8303426 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.9724. Min Act: -0.1700
Data Index: 2935796 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.9412. Min Act: -0.1700
Data Index: 6750118 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.9412. Min Act: -0.1700
Data Index: 2600812 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.9099. Min Act: -0.1700
Data Index: 3839637 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.9099. Min Act: -0.1700
Data Index: 4925617 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8787. Min Act: -0.1700
Data Index: 5727864 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8474. Min Act: -0.1700
Data Index: 6408064 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8474. Min Act: -0.1700
Data Index: 5193394 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8474. Min Act: -0.1700
Data Index: 24639 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8474. Min Act: -0.1700
Data Index: 4645220 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.8162. Min Act: -0.1700
Data Index: 7900950 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 7110612 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7849. Min Act: -0.1700
Data Index: 6752040 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1599. Min Range: -7.1599
Max Act: 6.7537. Min Act: -0.1700
Data Index: 5564130 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19