Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.3717. Min Act: -0.1700
Data Index: 1959427 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.3092. Min Act: -0.1700
Data Index: 4177316 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.2467. Min Act: -0.1700
Data Index: 6558144 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.2467. Min Act: -0.1700
Data Index: 4177315 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.2154. Min Act: -0.1700
Data Index: 7644958 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1842. Min Act: -0.1700
Data Index: 320997 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1529. Min Act: -0.1700
Data Index: 8391096 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1529. Min Act: -0.1700
Data Index: 643382 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1217. Min Act: -0.1700
Data Index: 5731918 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1217. Min Act: -0.1700
Data Index: 1574838 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1217. Min Act: -0.1700
Data Index: 8160556 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1217. Min Act: -0.1700
Data Index: 550474 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1217. Min Act: -0.1700
Data Index: 5731917 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.1217. Min Act: -0.1700
Data Index: 2489282 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.0904. Min Act: -0.1700
Data Index: 7126421 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.0592. Min Act: -0.1700
Data Index: 2180584 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.0592. Min Act: -0.1700
Data Index: 4875293 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.0592. Min Act: -0.1700
Data Index: 2379948 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.0904. Min Act: -0.1700
Data Index: 6926421 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3717. Min Range: -4.3717
Max Act: 4.0592. Min Act: -0.1700
Data Index: 3495629 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19