Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0952. Min Range: -7.0952
Max Act: 7.0952. Min Act: -0.1700
Data Index: 2400206 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.8140. Min Act: -0.1700
Data Index: 2187273 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.5640. Min Act: -0.1700
Data Index: 5050348 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.5015. Min Act: -0.1700
Data Index: 8682083 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.5327. Min Act: -0.1700
Data Index: 6220901 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.3765. Min Act: -0.1700
Data Index: 6561713 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.4390. Min Act: -0.1700
Data Index: 2497823 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.4077. Min Act: -0.1700
Data Index: 7728884 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.4077. Min Act: -0.1700
Data Index: 7926187 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.3765. Min Act: -0.1700
Data Index: 202458 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.3452. Min Act: -0.1700
Data Index: 6216005 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.3765. Min Act: -0.1700
Data Index: 8271476 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.3140. Min Act: -0.1700
Data Index: 1976372 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.3140. Min Act: -0.1700
Data Index: 3715775 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.2827. Min Act: -0.1700
Data Index: 29571 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.2827. Min Act: -0.1700
Data Index: 7620806 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.2827. Min Act: -0.1700
Data Index: 5935582 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.2515. Min Act: -0.1700
Data Index: 909902 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.2515. Min Act: -0.1700
Data Index: 4133729 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0952. Min Range: -7.0952
Max Act: 6.2202. Min Act: -0.1700
Data Index: 3125074 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19