Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6012 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1669. Min Range: -7.1669
Max Act: 7.1669. Min Act: -0.1700
Data Index: 2094580 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.8232. Min Act: -0.1700
Data Index: 7921964 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.7607. Min Act: -0.1700
Data Index: 136811 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.7919. Min Act: -0.1700
Data Index: 6483508 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6982. Min Act: -0.1700
Data Index: 1107804 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.7294. Min Act: -0.1700
Data Index: 3234908 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6982. Min Act: -0.1700
Data Index: 556453 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6982. Min Act: -0.1700
Data Index: 8671937 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6982. Min Act: -0.1700
Data Index: 7034448 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6669. Min Act: -0.1700
Data Index: 4433531 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6669. Min Act: -0.1700
Data Index: 2290118 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6357. Min Act: -0.1700
Data Index: 5465512 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6044. Min Act: -0.1700
Data Index: 5374639 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6357. Min Act: -0.1700
Data Index: 3689946 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6044. Min Act: -0.1700
Data Index: 3169213 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6357. Min Act: -0.1700
Data Index: 3259240 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6044. Min Act: -0.1700
Data Index: 365651 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6044. Min Act: -0.1700
Data Index: 1184031 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.5732. Min Act: -0.1700
Data Index: 2560959 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1669. Min Range: -7.1669
Max Act: 6.6044. Min Act: -0.1700
Data Index: 3043762 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19