Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0774. Min Range: -5.0774
Max Act: 5.0774. Min Act: -0.1700
Data Index: 4657754 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0774. Min Range: -5.0774
Max Act: 5.0149. Min Act: -0.1700
Data Index: 8509517 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.9212. Min Act: -0.1700
Data Index: 3477838 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.9212. Min Act: -0.1700
Data Index: 775747 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.8274. Min Act: -0.1700
Data Index: 2686599 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.8587. Min Act: -0.1700
Data Index: 3486441 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7962. Min Act: -0.1700
Data Index: 3641846 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7962. Min Act: -0.1700
Data Index: 5404008 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7649. Min Act: -0.1700
Data Index: 7673917 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7649. Min Act: -0.1700
Data Index: 1441710 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7337. Min Act: -0.1700
Data Index: 6144633 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7337. Min Act: -0.1700
Data Index: 7475532 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7337. Min Act: -0.1700
Data Index: 1828319 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7337. Min Act: -0.1700
Data Index: 7651506 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7337. Min Act: -0.1700
Data Index: 3671574 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.7024. Min Act: -0.1700
Data Index: 127788 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.6712. Min Act: -0.1700
Data Index: 2499327 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.6712. Min Act: -0.1700
Data Index: 8050069 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.6712. Min Act: -0.1700
Data Index: 4090453 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0774. Min Range: -5.0774
Max Act: 4.6399. Min Act: -0.1700
Data Index: 5554325 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19