Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 453 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.9132. Min Act: -0.1700
Data Index: 6358315 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7882. Min Act: -0.1700
Data Index: 8594861 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7569. Min Act: -0.1700
Data Index: 2192036 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7569. Min Act: -0.1700
Data Index: 4862125 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7569. Min Act: -0.1700
Data Index: 5278111 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.7257. Min Act: -0.1700
Data Index: 8127852 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6632. Min Act: -0.1700
Data Index: 3535365 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6944. Min Act: -0.1700
Data Index: 1730628 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 1378390 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6944. Min Act: -0.1700
Data Index: 2184998 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 1773608 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6632. Min Act: -0.1700
Data Index: 5504918 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6632. Min Act: -0.1700
Data Index: 8505410 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 6990869 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 4220256 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 73011 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6319. Min Act: -0.1700
Data Index: 5167233 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6007. Min Act: -0.1700
Data Index: 1715501 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.6007. Min Act: -0.1700
Data Index: 7000353 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9132. Min Range: -4.9132
Max Act: 4.5694. Min Act: -0.1700
Data Index: 3721094 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19