Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.8129. Min Act: -0.1700
Data Index: 4954611 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7973. Min Act: -0.1700
Data Index: 7058827 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7660. Min Act: -0.1700
Data Index: 1293900 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7660. Min Act: -0.1700
Data Index: 4637332 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7504. Min Act: -0.1700
Data Index: 7597993 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7504. Min Act: -0.1700
Data Index: 6483390 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7348. Min Act: -0.1700
Data Index: 6838643 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7348. Min Act: -0.1700
Data Index: 2549062 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7191. Min Act: -0.1700
Data Index: 5408432 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7191. Min Act: -0.1700
Data Index: 3965837 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7191. Min Act: -0.1700
Data Index: 8761943 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7035. Min Act: -0.1700
Data Index: 474460 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.7035. Min Act: -0.1700
Data Index: 7413000 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.6722. Min Act: -0.1700
Data Index: 3125749 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.6878. Min Act: -0.1700
Data Index: 2117609 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.6878. Min Act: -0.1700
Data Index: 3755254 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.6722. Min Act: -0.1700
Data Index: 4979405 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.6565. Min Act: -0.1700
Data Index: 2053068 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.6878. Min Act: -0.1700
Data Index: 6876693 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8129. Min Range: -3.8129
Max Act: 3.6878. Min Act: -0.1700
Data Index: 5519598 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19