Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 430 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.3783. Min Act: -0.1700
Data Index: 7888465 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.3158. Min Act: -0.1700
Data Index: 3274668 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.2533. Min Act: -0.1700
Data Index: 2841773 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.2533. Min Act: -0.1700
Data Index: 8801108 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.2220. Min Act: -0.1700
Data Index: 6265059 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.2220. Min Act: -0.1700
Data Index: 6260888 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.2220. Min Act: -0.1700
Data Index: 4312860 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1908. Min Act: -0.1700
Data Index: 2742800 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1908. Min Act: -0.1700
Data Index: 2544161 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1595. Min Act: -0.1700
Data Index: 8417680 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1595. Min Act: -0.1700
Data Index: 5829912 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1595. Min Act: -0.1700
Data Index: 5611234 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1595. Min Act: -0.1700
Data Index: 3339020 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1283. Min Act: -0.1700
Data Index: 8001134 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1283. Min Act: -0.1700
Data Index: 8173495 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1283. Min Act: -0.1700
Data Index: 2020479 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1283. Min Act: -0.1700
Data Index: 1565940 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.1595. Min Act: -0.1700
Data Index: 4467823 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.0970. Min Act: -0.1700
Data Index: 2982743 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3783. Min Range: -4.3783
Max Act: 4.0658. Min Act: -0.1700
Data Index: 1461765 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19