Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0009. Min Range: -7.0009
Max Act: 7.0009. Min Act: -0.1700
Data Index: 4667980 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0009. Min Range: -7.0009
Max Act: 7.0009. Min Act: -0.1700
Data Index: 3406514 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.9384. Min Act: -0.1700
Data Index: 6355517 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.9072. Min Act: -0.1700
Data Index: 3278408 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.9384. Min Act: -0.1700
Data Index: 3107108 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8759. Min Act: -0.1700
Data Index: 7008855 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8759. Min Act: -0.1700
Data Index: 6951315 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8134. Min Act: -0.1700
Data Index: 7775968 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8134. Min Act: -0.1700
Data Index: 7106496 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7509. Min Act: -0.1700
Data Index: 1256678 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7509. Min Act: -0.1700
Data Index: 4004983 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7509. Min Act: -0.1700
Data Index: 5191798 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6884. Min Act: -0.1700
Data Index: 5803232 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7509. Min Act: -0.1700
Data Index: 5509959 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7197. Min Act: -0.1700
Data Index: 4401790 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6884. Min Act: -0.1700
Data Index: 8632430 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7197. Min Act: -0.1700
Data Index: 2275480 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6884. Min Act: -0.1700
Data Index: 8655501 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6884. Min Act: -0.1700
Data Index: 2055055 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6572. Min Act: -0.1700
Data Index: 5837297 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19