Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.6623. Min Act: -0.1700
Data Index: 7734982 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.6623. Min Act: -0.1700
Data Index: 1419655 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.5998. Min Act: -0.1700
Data Index: 6317907 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.5373. Min Act: -0.1700
Data Index: 3918369 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.5373. Min Act: -0.1700
Data Index: 4589792 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.5373. Min Act: -0.1700
Data Index: 8243147 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.5373. Min Act: -0.1700
Data Index: 534606 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.5373. Min Act: -0.1700
Data Index: 5120119 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.5373. Min Act: -0.1700
Data Index: 8596995 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4748. Min Act: -0.1700
Data Index: 6808524 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4748. Min Act: -0.1700
Data Index: 8001500 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4748. Min Act: -0.1700
Data Index: 3953513 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4435. Min Act: -0.1700
Data Index: 1181953 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4435. Min Act: -0.1700
Data Index: 3160978 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4435. Min Act: -0.1700
Data Index: 2938455 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4435. Min Act: -0.1700
Data Index: 7155044 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4123. Min Act: -0.1700
Data Index: 5918172 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.4123. Min Act: -0.1700
Data Index: 6747517 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.3810. Min Act: -0.1700
Data Index: 7944158 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6623. Min Range: -7.6623
Max Act: 7.3810. Min Act: -0.1700
Data Index: 921954 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19