Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1329 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.5623. Min Act: -0.1700
Data Index: 374129 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.4373. Min Act: -0.1700
Data Index: 8808957 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.3748. Min Act: -0.1700
Data Index: 2056236 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.3123. Min Act: -0.1700
Data Index: 1523044 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.1873. Min Act: -0.1700
Data Index: 6616739 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.0623. Min Act: -0.1700
Data Index: 2748650 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.0623. Min Act: -0.1700
Data Index: 5196035 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.0623. Min Act: -0.1700
Data Index: 3668680 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.0623. Min Act: -0.1700
Data Index: 8559389 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.0623. Min Act: -0.1700
Data Index: 5023859 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5623. Min Range: -8.5623
Max Act: 8.0623. Min Act: -0.1700
Data Index: 503032 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.8748. Min Act: -0.1700
Data Index: 6927025 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.8748. Min Act: -0.1700
Data Index: 8422061 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.8123. Min Act: -0.1700
Data Index: 179206 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.8123. Min Act: -0.1700
Data Index: 8103681 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.8123. Min Act: -0.1700
Data Index: 288212 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.8123. Min Act: -0.1700
Data Index: 5504063 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.6873. Min Act: -0.1700
Data Index: 3042960 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.7498. Min Act: -0.1700
Data Index: 3364378 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5623. Min Range: -8.5623
Max Act: 7.7498. Min Act: -0.1700
Data Index: 8827602 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19