Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.6079. Min Act: -0.1700
Data Index: 3342181 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.5454. Min Act: -0.1700
Data Index: 5202769 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.2017. Min Act: -0.1700
Data Index: 6167928 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.1392. Min Act: -0.1700
Data Index: 11509 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.1079. Min Act: -0.1700
Data Index: 6857861 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.0767. Min Act: -0.1700
Data Index: 7321326 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.0454. Min Act: -0.1700
Data Index: 7755942 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.0142. Min Act: -0.1700
Data Index: 789626 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.0142. Min Act: -0.1700
Data Index: 3193111 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6079. Min Range: -7.6079
Max Act: 7.0142. Min Act: -0.1700
Data Index: 3179385 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.9204. Min Act: -0.1700
Data Index: 4885053 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8892. Min Act: -0.1700
Data Index: 6073090 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8892. Min Act: -0.1700
Data Index: 3242952 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8892. Min Act: -0.1700
Data Index: 1006003 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8579. Min Act: -0.1700
Data Index: 3883572 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8579. Min Act: -0.1700
Data Index: 5261198 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8579. Min Act: -0.1700
Data Index: 971146 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8579. Min Act: -0.1700
Data Index: 1153301 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8579. Min Act: -0.1700
Data Index: 1778906 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6079. Min Range: -7.6079
Max Act: 6.8579. Min Act: -0.1700
Data Index: 8495326 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19