Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 220 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.6299. Min Act: -0.1700
Data Index: 5953933 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.4890. Min Act: -0.1700
Data Index: 4949876 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.4263. Min Act: -0.1700
Data Index: 4105052 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.4263. Min Act: -0.1700
Data Index: 4105054 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.3950. Min Act: -0.1700
Data Index: 4105051 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.3950. Min Act: -0.1700
Data Index: 3053726 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.3793. Min Act: -0.1700
Data Index: 2665491 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.3950. Min Act: -0.1700
Data Index: 1193714 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.3636. Min Act: -0.1700
Data Index: 4105053 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.3322. Min Act: -0.1700
Data Index: 7125399 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2694. Min Act: -0.1700
Data Index: 942101 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.3008. Min Act: -0.1700
Data Index: 3522223 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2694. Min Act: -0.1700
Data Index: 123770 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2694. Min Act: -0.1700
Data Index: 18095 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2380. Min Act: -0.1700
Data Index: 4105062 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2537. Min Act: -0.1700
Data Index: 3295648 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.1908. Min Act: -0.1700
Data Index: 1449271 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2537. Min Act: -0.1700
Data Index: 5149615 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2066. Min Act: -0.1700
Data Index: 706362 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6299. Min Range: -3.6299
Max Act: 3.2223. Min Act: -0.1700
Data Index: 3652300 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19