Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4966 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.6455. Min Act: -0.1700
Data Index: 1067843 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.5830. Min Act: -0.1700
Data Index: 5952593 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.3330. Min Act: -0.1700
Data Index: 7358064 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.3330. Min Act: -0.1700
Data Index: 7696025 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.3330. Min Act: -0.1700
Data Index: 6124107 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.3330. Min Act: -0.1700
Data Index: 524223 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.2705. Min Act: -0.1700
Data Index: 179755 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.2080. Min Act: -0.1700
Data Index: 7906706 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 67567 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.2080. Min Act: -0.1700
Data Index: 4174133 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.2080. Min Act: -0.1700
Data Index: 2527563 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 1054180 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 6624725 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 4049635 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 2872032 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 3147910 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 7622836 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 2291587 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.1455. Min Act: -0.1700
Data Index: 2694079 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6455. Min Range: -9.6455
Max Act: 9.0830. Min Act: -0.1700
Data Index: 4395531 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19