Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5338 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.5418. Min Act: -0.1700
Data Index: 6927824 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.5106. Min Act: -0.1700
Data Index: 5069595 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.3543. Min Act: -0.1700
Data Index: 7965507 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.2918. Min Act: -0.1700
Data Index: 3078852 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.3231. Min Act: -0.1700
Data Index: 1162262 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.2293. Min Act: -0.1700
Data Index: 1932136 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.2293. Min Act: -0.1700
Data Index: 3112680 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1981. Min Act: -0.1700
Data Index: 7095295 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1981. Min Act: -0.1700
Data Index: 3475578 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1981. Min Act: -0.1700
Data Index: 7563194 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1355. Min Act: -0.1700
Data Index: 1157570 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1355. Min Act: -0.1700
Data Index: 7064180 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1355. Min Act: -0.1700
Data Index: 6891077 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1043. Min Act: -0.1700
Data Index: 4276276 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1043. Min Act: -0.1700
Data Index: 3123938 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1355. Min Act: -0.1700
Data Index: 6091501 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1043. Min Act: -0.1700
Data Index: 2900287 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.1043. Min Act: -0.1700
Data Index: 151193 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.0730. Min Act: -0.1700
Data Index: 6859185 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5418. Min Range: -4.5418
Max Act: 4.0730. Min Act: -0.1700
Data Index: 3231815 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19