Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.8876. Min Act: -0.1700
Data Index: 370921 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.8876. Min Act: -0.1700
Data Index: 6162605 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.7938. Min Act: -0.1700
Data Index: 7126802 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.7938. Min Act: -0.1700
Data Index: 2481475 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.7938. Min Act: -0.1700
Data Index: 2342348 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.7001. Min Act: -0.1700
Data Index: 61426 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5702417 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6688. Min Act: -0.1700
Data Index: 7014136 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6688. Min Act: -0.1700
Data Index: 6741235 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6063. Min Act: -0.1700
Data Index: 5479303 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6063. Min Act: -0.1700
Data Index: 7230082 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6063. Min Act: -0.1700
Data Index: 3346312 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6063. Min Act: -0.1700
Data Index: 2715208 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.5751. Min Act: -0.1700
Data Index: 6567629 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6376. Min Act: -0.1700
Data Index: 3925301 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.6063. Min Act: -0.1700
Data Index: 1900522 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.5751. Min Act: -0.1700
Data Index: 5474463 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.5751. Min Act: -0.1700
Data Index: 1756283 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.5751. Min Act: -0.1700
Data Index: 2845118 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8876. Min Range: -5.8876
Max Act: 5.5751. Min Act: -0.1700
Data Index: 1621790 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19