Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0990. Min Range: -5.0990
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3735851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0990. Min Range: -5.0990
Max Act: 5.0677. Min Act: -0.1700
Data Index: 1903091 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0990. Min Range: -5.0990
Max Act: 5.0677. Min Act: -0.1700
Data Index: 3082213 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0990. Min Range: -5.0990
Max Act: 5.0052. Min Act: -0.1696
Data Index: 5724802 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9740. Min Act: -0.1700
Data Index: 498426 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9740. Min Act: -0.1700
Data Index: 4593515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9740. Min Act: -0.1700
Data Index: 439939 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 5714924 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 4711140 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9427. Min Act: -0.1700
Data Index: 7222824 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9115. Min Act: -0.1700
Data Index: 1776123 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9115. Min Act: -0.1699
Data Index: 8534251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9115. Min Act: -0.1700
Data Index: 8043991 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9115. Min Act: -0.1700
Data Index: 2898165 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.9115. Min Act: -0.1700
Data Index: 1101411 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.8802. Min Act: -0.1691
Data Index: 5098085 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.8802. Min Act: -0.1700
Data Index: 1018301 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.8802. Min Act: -0.1700
Data Index: 4747004 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.8802. Min Act: -0.1699
Data Index: 2215593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0990. Min Range: -5.0990
Max Act: 4.8490. Min Act: -0.1700
Data Index: 5814465 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19