Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5196 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.6003. Min Act: -0.1700
Data Index: 6691373 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.4441. Min Act: -0.1700
Data Index: 1733505 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.3816. Min Act: -0.1700
Data Index: 2761432 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.2566. Min Act: -0.1700
Data Index: 4414496 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.2566. Min Act: -0.1700
Data Index: 6188838 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.2253. Min Act: -0.1700
Data Index: 7844613 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.1628. Min Act: -0.1700
Data Index: 8087734 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.1316. Min Act: -0.1700
Data Index: 6589537 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.1316. Min Act: -0.1700
Data Index: 4725615 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.0378. Min Act: -0.1700
Data Index: 398538 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.0691. Min Act: -0.1700
Data Index: 6158425 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.0691. Min Act: -0.1700
Data Index: 2428091 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.0691. Min Act: -0.1700
Data Index: 6298393 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.0378. Min Act: -0.1700
Data Index: 3705065 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.0378. Min Act: -0.1700
Data Index: 3962739 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6003. Min Range: -6.6003
Max Act: 5.9753. Min Act: -0.1700
Data Index: 7681203 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6003. Min Range: -6.6003
Max Act: 6.0066. Min Act: -0.1700
Data Index: 1241715 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6003. Min Range: -6.6003
Max Act: 5.9441. Min Act: -0.1700
Data Index: 8783049 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6003. Min Range: -6.6003
Max Act: 5.9441. Min Act: -0.1700
Data Index: 7844614 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6003. Min Range: -6.6003
Max Act: 5.9441. Min Act: -0.1700
Data Index: 2233145 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19