Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2389 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.4941. Min Act: -0.1700
Data Index: 7862700 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.3379. Min Act: -0.1700
Data Index: 1017406 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.3066. Min Act: -0.1700
Data Index: 4267324 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2754. Min Act: -0.1700
Data Index: 7187523 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2754. Min Act: -0.1700
Data Index: 789377 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2441. Min Act: -0.1700
Data Index: 7449082 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2441. Min Act: -0.1700
Data Index: 716224 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2441. Min Act: -0.1700
Data Index: 4886588 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2441. Min Act: -0.1700
Data Index: 8419330 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2129. Min Act: -0.1700
Data Index: 2854512 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2441. Min Act: -0.1700
Data Index: 4861171 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2129. Min Act: -0.1700
Data Index: 8289372 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.1816. Min Act: -0.1700
Data Index: 3477324 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.1504. Min Act: -0.1700
Data Index: 4966311 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.2129. Min Act: -0.1700
Data Index: 2816270 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.1504. Min Act: -0.1700
Data Index: 4272929 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.1191. Min Act: -0.1700
Data Index: 683372 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.1504. Min Act: -0.1700
Data Index: 349061 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.1504. Min Act: -0.1700
Data Index: 4125844 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4941. Min Range: -6.4941
Max Act: 6.1504. Min Act: -0.1700
Data Index: 6131966 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19