Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4725 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6437. Min Range: -7.6437
Max Act: 7.6437. Min Act: -0.1700
Data Index: 2313562 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6437. Min Range: -7.6437
Max Act: 7.4249. Min Act: -0.1700
Data Index: 854313 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6437. Min Range: -7.6437
Max Act: 7.2062. Min Act: -0.1700
Data Index: 2847165 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6437. Min Range: -7.6437
Max Act: 7.1437. Min Act: -0.1700
Data Index: 4066350 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6437. Min Range: -7.6437
Max Act: 7.1124. Min Act: -0.1700
Data Index: 1557259 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6437. Min Range: -7.6437
Max Act: 7.0812. Min Act: -0.1700
Data Index: 4413103 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.9874. Min Act: -0.1700
Data Index: 41939 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.9874. Min Act: -0.1700
Data Index: 2202767 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.8937. Min Act: -0.1700
Data Index: 854312 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7999. Min Act: -0.1700
Data Index: 4066352 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7999. Min Act: -0.1700
Data Index: 6213443 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7999. Min Act: -0.1700
Data Index: 5591590 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7999. Min Act: -0.1700
Data Index: 7123466 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7687. Min Act: -0.1700
Data Index: 5142120 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7687. Min Act: -0.1700
Data Index: 3176298 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7374. Min Act: -0.1700
Data Index: 4255977 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.7062. Min Act: -0.1700
Data Index: 281709 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.6437. Min Act: -0.1700
Data Index: 2487534 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7006948 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6437. Min Range: -7.6437
Max Act: 6.6437. Min Act: -0.1700
Data Index: 2682820 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19