Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.7733. Min Act: -0.1700
Data Index: 7264784 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.6132. Min Act: -0.1700
Data Index: 4467575 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.5649. Min Act: -0.1700
Data Index: 2929418 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4840. Min Act: -0.1700
Data Index: 2692794 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.5002. Min Act: -0.1700
Data Index: 1997411 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4515. Min Act: -0.1700
Data Index: 7015177 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4840. Min Act: -0.1700
Data Index: 3261878 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4515. Min Act: -0.1700
Data Index: 5350194 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4353. Min Act: -0.1700
Data Index: 2297502 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4678. Min Act: -0.1700
Data Index: 5659859 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4515. Min Act: -0.1700
Data Index: 7783866 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4190. Min Act: -0.1700
Data Index: 8043315 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4353. Min Act: -0.1700
Data Index: 5195973 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4190. Min Act: -0.1700
Data Index: 1406160 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4027. Min Act: -0.1700
Data Index: 3377448 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4027. Min Act: -0.1700
Data Index: 171348 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.3863. Min Act: -0.1700
Data Index: 2738305 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4027. Min Act: -0.1700
Data Index: 745384 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4027. Min Act: -0.1700
Data Index: 1978074 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7733. Min Range: -2.7733
Max Act: 2.4027. Min Act: -0.1700
Data Index: 3921432 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19