Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4390. Min Act: -0.1700
Data Index: 3906985 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4390. Min Act: -0.1700
Data Index: 7144369 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4077. Min Act: -0.1700
Data Index: 1113901 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3920. Min Act: -0.1700
Data Index: 7823513 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 4799662 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3449. Min Act: -0.1700
Data Index: 6376265 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3292. Min Act: -0.1700
Data Index: 223166 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2979. Min Act: -0.1700
Data Index: 6265656 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3136. Min Act: -0.1700
Data Index: 3359026 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2979. Min Act: -0.1700
Data Index: 2457133 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2979. Min Act: -0.1700
Data Index: 442575 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2822. Min Act: -0.1700
Data Index: 7864867 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2822. Min Act: -0.1700
Data Index: 6031190 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2979. Min Act: -0.1700
Data Index: 4220024 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2822. Min Act: -0.1700
Data Index: 6513660 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2979. Min Act: -0.1700
Data Index: 6630422 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2664. Min Act: -0.1700
Data Index: 3430855 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2664. Min Act: -0.1700
Data Index: 7653747 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2664. Min Act: -0.1700
Data Index: 1204999 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2350. Min Act: -0.1700
Data Index: 7164983 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19