Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.3168. Min Act: -0.1698
Data Index: 663764 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.3168. Min Act: -0.1700
Data Index: 2737060 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.3004. Min Act: -0.1700
Data Index: 103429 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2839. Min Act: -0.1700
Data Index: 891219 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2674. Min Act: -0.1700
Data Index: 8574680 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2344. Min Act: -0.1700
Data Index: 7558863 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2344. Min Act: -0.1700
Data Index: 1654546 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 7694878 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 8524307 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2344. Min Act: -0.1700
Data Index: 1535660 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2344. Min Act: -0.1700
Data Index: 5531994 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 2199959 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 1845211 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 4617737 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 622599 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2344. Min Act: -0.1700
Data Index: 6385679 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 841940 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 2323426 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2178. Min Act: -0.1700
Data Index: 7099474 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3168. Min Range: -2.3168
Max Act: 2.2012. Min Act: -0.1700
Data Index: 7011858 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19