Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.1565. Min Act: -0.1700
Data Index: 8548881 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.1252. Min Act: -0.1700
Data Index: 287718 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.1252. Min Act: -0.1700
Data Index: 5080558 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.0940. Min Act: -0.1700
Data Index: 426151 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.0315. Min Act: -0.1700
Data Index: 4036921 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.0940. Min Act: -0.1700
Data Index: 7981320 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.0002. Min Act: -0.1700
Data Index: 3852876 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.0002. Min Act: -0.1700
Data Index: 3124450 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.0002. Min Act: -0.1700
Data Index: 3369916 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9377. Min Act: -0.1700
Data Index: 4548550 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9065. Min Act: -0.1700
Data Index: 4233686 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1565. Min Range: -6.1565
Max Act: 6.0002. Min Act: -0.1700
Data Index: 3437017 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9690. Min Act: -0.1700
Data Index: 6976927 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9690. Min Act: -0.1700
Data Index: 5062635 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9377. Min Act: -0.1700
Data Index: 1989545 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9690. Min Act: -0.1700
Data Index: 8489104 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9377. Min Act: -0.1700
Data Index: 4667047 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.9065. Min Act: -0.1700
Data Index: 1800993 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.8752. Min Act: -0.1700
Data Index: 4739567 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1565. Min Range: -6.1565
Max Act: 5.8752. Min Act: -0.1700
Data Index: 1408466 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19