Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4239 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.8801. Min Act: -0.1700
Data Index: 3399956 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.4426. Min Act: -0.1700
Data Index: 638215 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.3801. Min Act: -0.1700
Data Index: 8528454 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.3801. Min Act: -0.1700
Data Index: 7999774 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.3488. Min Act: -0.1700
Data Index: 733802 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.2238. Min Act: -0.1700
Data Index: 665668 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.2238. Min Act: -0.1700
Data Index: 7530780 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1926. Min Act: -0.1700
Data Index: 5232130 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1926. Min Act: -0.1700
Data Index: 4027578 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1926. Min Act: -0.1700
Data Index: 4512876 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1301. Min Act: -0.1700
Data Index: 3813086 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1613. Min Act: -0.1700
Data Index: 8113527 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1613. Min Act: -0.1700
Data Index: 740226 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1301. Min Act: -0.1700
Data Index: 2080660 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1301. Min Act: -0.1700
Data Index: 2296609 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1301. Min Act: -0.1700
Data Index: 2321 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.0988. Min Act: -0.1700
Data Index: 3141680 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.0676. Min Act: -0.1700
Data Index: 129477 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.0676. Min Act: -0.1700
Data Index: 2696781 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.0363. Min Act: -0.1700
Data Index: 827788 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19