Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1343 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.6769. Min Act: -0.1700
Data Index: 360283 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1459409 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.3332. Min Act: -0.1700
Data Index: 8197469 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.2707. Min Act: -0.1700
Data Index: 4997574 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.2394. Min Act: -0.1700
Data Index: 1620998 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.2082. Min Act: -0.1700
Data Index: 8094601 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.1769. Min Act: -0.1700
Data Index: 8000179 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.1769. Min Act: -0.1700
Data Index: 4094726 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0832. Min Act: -0.1700
Data Index: 8438671 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.1144. Min Act: -0.1700
Data Index: 987653 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.1144. Min Act: -0.1700
Data Index: 5877032 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0832. Min Act: -0.1700
Data Index: 3512943 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0519. Min Act: -0.1700
Data Index: 351388 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0519. Min Act: -0.1700
Data Index: 8192435 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0519. Min Act: -0.1700
Data Index: 4857244 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0519. Min Act: -0.1700
Data Index: 3567120 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0206. Min Act: -0.1700
Data Index: 6579645 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6769. Min Range: -4.6769
Max Act: 3.9894. Min Act: -0.1700
Data Index: 2726111 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0519. Min Act: -0.1700
Data Index: 1735502 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6769. Min Range: -4.6769
Max Act: 4.0519. Min Act: -0.1700
Data Index: 1422095 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19