Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0110. Min Range: -4.0110
Max Act: 4.0110. Min Act: -0.1700
Data Index: 2633613 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.9485. Min Act: -0.1700
Data Index: 7024679 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.9172. Min Act: -0.1700
Data Index: 8048053 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.8859. Min Act: -0.1700
Data Index: 6918799 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.9172. Min Act: -0.1700
Data Index: 2328296 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.8859. Min Act: -0.1700
Data Index: 6056389 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.8547. Min Act: -0.1700
Data Index: 7155667 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.8547. Min Act: -0.1700
Data Index: 8266133 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7921. Min Act: -0.1700
Data Index: 7288015 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7921. Min Act: -0.1700
Data Index: 5523722 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7921. Min Act: -0.1700
Data Index: 1403537 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7609. Min Act: -0.1700
Data Index: 5987002 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7921. Min Act: -0.1700
Data Index: 2889652 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7609. Min Act: -0.1700
Data Index: 1835700 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7921. Min Act: -0.1700
Data Index: 4664693 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7609. Min Act: -0.1700
Data Index: 6056388 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7921. Min Act: -0.1700
Data Index: 6204291 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7609. Min Act: -0.1700
Data Index: 2688587 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7609. Min Act: -0.1700
Data Index: 5942174 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7609. Min Act: -0.1700
Data Index: 3146844 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19