Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.8747. Min Act: -0.1700
Data Index: 8673269 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.8435. Min Act: -0.1700
Data Index: 8349215 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.8435. Min Act: -0.1700
Data Index: 2529167 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.7497. Min Act: -0.1700
Data Index: 7772053 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.7497. Min Act: -0.1700
Data Index: 5477254 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.7185. Min Act: -0.1700
Data Index: 6216282 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.6247. Min Act: -0.1700
Data Index: 2280572 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.6560. Min Act: -0.1700
Data Index: 6887480 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.6560. Min Act: -0.1700
Data Index: 6793873 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.6560. Min Act: -0.1700
Data Index: 8686557 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.6247. Min Act: -0.1700
Data Index: 7329441 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.6247. Min Act: -0.1700
Data Index: 8736980 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5935. Min Act: -0.1700
Data Index: 2010887 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5935. Min Act: -0.1700
Data Index: 2995394 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5622. Min Act: -0.1700
Data Index: 2973874 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5622. Min Act: -0.1700
Data Index: 6328488 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5622. Min Act: -0.1700
Data Index: 5556997 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5935. Min Act: -0.1700
Data Index: 7696892 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5622. Min Act: -0.1700
Data Index: 1955178 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8747. Min Range: -6.8747
Max Act: 6.5622. Min Act: -0.1700
Data Index: 7975810 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19