Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6175 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0803. Min Range: -5.0803
Max Act: 5.0803. Min Act: -0.1700
Data Index: 5935826 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8616. Min Act: -0.1700
Data Index: 7861906 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8303. Min Act: -0.1700
Data Index: 1241598 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8303. Min Act: -0.1700
Data Index: 8803871 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8616. Min Act: -0.1700
Data Index: 3370342 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8303. Min Act: -0.1700
Data Index: 8518847 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.8303. Min Act: -0.1700
Data Index: 5096517 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7991. Min Act: -0.1700
Data Index: 4717678 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7991. Min Act: -0.1700
Data Index: 4630831 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7678. Min Act: -0.1700
Data Index: 2860952 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7678. Min Act: -0.1700
Data Index: 984702 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7991. Min Act: -0.1700
Data Index: 5850622 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7678. Min Act: -0.1700
Data Index: 7182336 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7678. Min Act: -0.1700
Data Index: 7099468 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7366. Min Act: -0.1700
Data Index: 2912739 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7366. Min Act: -0.1700
Data Index: 221979 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7366. Min Act: -0.1700
Data Index: 1069380 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7053. Min Act: -0.1700
Data Index: 5031635 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7053. Min Act: -0.1700
Data Index: 1403168 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0803. Min Range: -5.0803
Max Act: 4.7053. Min Act: -0.1700
Data Index: 1877417 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19