Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5059 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0732. Min Range: -5.0732
Max Act: 5.0732. Min Act: -0.1700
Data Index: 5558214 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0732. Min Range: -5.0732
Max Act: 5.0419. Min Act: -0.1700
Data Index: 2220939 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0732. Min Range: -5.0732
Max Act: 5.0107. Min Act: -0.1700
Data Index: 6025279 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.9482. Min Act: -0.1700
Data Index: 2159440 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8857. Min Act: -0.1700
Data Index: 5405763 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8232. Min Act: -0.1700
Data Index: 2000137 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8544. Min Act: -0.1700
Data Index: 1261206 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8544. Min Act: -0.1700
Data Index: 6867059 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8232. Min Act: -0.1700
Data Index: 6025281 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7919. Min Act: -0.1700
Data Index: 3919061 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7919. Min Act: -0.1700
Data Index: 3834597 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7919. Min Act: -0.1700
Data Index: 8574990 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7919. Min Act: -0.1700
Data Index: 1363390 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 679173 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 2752444 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1693
Data Index: 6863757 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 2769079 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7294. Min Act: -0.1700
Data Index: 119991 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 5797361 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 704573 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19