Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.5727. Min Act: -0.1700
Data Index: 4615080 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.4317. Min Act: -0.1700
Data Index: 579220 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.4160. Min Act: -0.1700
Data Index: 2471322 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.4003. Min Act: -0.1700
Data Index: 1236197 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3847. Min Act: -0.1700
Data Index: 4513932 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3690. Min Act: -0.1700
Data Index: 8508169 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3219. Min Act: -0.1700
Data Index: 7462615 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3533. Min Act: -0.1700
Data Index: 5397206 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3219. Min Act: -0.1700
Data Index: 7399069 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3376. Min Act: -0.1700
Data Index: 3787720 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3219. Min Act: -0.1700
Data Index: 8575959 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3219. Min Act: -0.1700
Data Index: 7351506 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.3062. Min Act: -0.1700
Data Index: 3579095 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.2905. Min Act: -0.1700
Data Index: 3027269 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.2905. Min Act: -0.1700
Data Index: 4081297 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.2748. Min Act: -0.1700
Data Index: 4394141 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.2905. Min Act: -0.1700
Data Index: 5841501 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.2748. Min Act: -0.1700
Data Index: 2904414 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.2905. Min Act: -0.1700
Data Index: 3604533 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5727. Min Range: -3.5727
Max Act: 3.2591. Min Act: -0.1700
Data Index: 5987058 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19