Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 613 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.4872. Min Act: -0.1700
Data Index: 7024732 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.4872. Min Act: -0.1700
Data Index: 8371106 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.4247. Min Act: -0.1700
Data Index: 2567559 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.2997. Min Act: -0.1700
Data Index: 8563634 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.3622. Min Act: -0.1700
Data Index: 7644967 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.2372. Min Act: -0.1700
Data Index: 4243054 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.1747. Min Act: -0.1700
Data Index: 5629075 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.1747. Min Act: -0.1700
Data Index: 5469262 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.1122. Min Act: -0.1700
Data Index: 5613833 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.1122. Min Act: -0.1700
Data Index: 8652052 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.0809. Min Act: -0.1700
Data Index: 8193434 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.0497. Min Act: -0.1700
Data Index: 6288368 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.0497. Min Act: -0.1700
Data Index: 3949568 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.0497. Min Act: -0.1700
Data Index: 8498445 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.0184. Min Act: -0.1700
Data Index: 5883269 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4872. Min Range: -8.4872
Max Act: 8.0184. Min Act: -0.1700
Data Index: 5072032 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4872. Min Range: -8.4872
Max Act: 7.9872. Min Act: -0.1700
Data Index: 7178297 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4872. Min Range: -8.4872
Max Act: 7.9559. Min Act: -0.1700
Data Index: 5099438 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4872. Min Range: -8.4872
Max Act: 7.9247. Min Act: -0.1700
Data Index: 6983943 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4872. Min Range: -8.4872
Max Act: 7.8934. Min Act: -0.1700
Data Index: 2290254 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19