Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5975 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6544. Min Range: -8.6544
Max Act: 8.6544. Min Act: -0.1700
Data Index: 8536916 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6544. Min Range: -8.6544
Max Act: 8.5919. Min Act: -0.1700
Data Index: 1180458 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6544. Min Range: -8.6544
Max Act: 8.3419. Min Act: -0.1700
Data Index: 1420775 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6544. Min Range: -8.6544
Max Act: 8.1857. Min Act: -0.1700
Data Index: 3982972 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.9044. Min Act: -0.1700
Data Index: 2900079 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.9044. Min Act: -0.1700
Data Index: 509006 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.7794. Min Act: -0.1700
Data Index: 3833948 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.8107. Min Act: -0.1700
Data Index: 7446217 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.7794. Min Act: -0.1700
Data Index: 7446220 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.7482. Min Act: -0.1700
Data Index: 7446216 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.6857. Min Act: -0.1700
Data Index: 7446222 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.6232. Min Act: -0.1700
Data Index: 4045629 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.6857. Min Act: -0.1700
Data Index: 7446211 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.6544. Min Act: -0.1700
Data Index: 7446210 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.6544. Min Act: -0.1700
Data Index: 7446208 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.5607. Min Act: -0.1700
Data Index: 4692879 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.6232. Min Act: -0.1700
Data Index: 7446223 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.4982. Min Act: -0.1700
Data Index: 7446218 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.4982. Min Act: -0.1700
Data Index: 5595209 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6544. Min Range: -8.6544
Max Act: 7.4669. Min Act: -0.1700
Data Index: 6771549 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19