Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1844 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1297. Min Range: -6.1297
Max Act: 6.1297. Min Act: -0.1700
Data Index: 957413 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1297. Min Range: -6.1297
Max Act: 6.1297. Min Act: -0.1700
Data Index: 8745259 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.9734. Min Act: -0.1700
Data Index: 694642 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.9734. Min Act: -0.1700
Data Index: 61614 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.9734. Min Act: -0.1700
Data Index: 4000783 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.8797. Min Act: -0.1700
Data Index: 178407 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.9109. Min Act: -0.1700
Data Index: 3998923 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.9109. Min Act: -0.1700
Data Index: 2083085 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.8172. Min Act: -0.1700
Data Index: 7199695 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.8172. Min Act: -0.1700
Data Index: 3384968 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7859. Min Act: -0.1700
Data Index: 3777700 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7859. Min Act: -0.1700
Data Index: 2516545 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7859. Min Act: -0.1700
Data Index: 4701744 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7547. Min Act: -0.1700
Data Index: 2259208 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7547. Min Act: -0.1700
Data Index: 1235390 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7859. Min Act: -0.1700
Data Index: 3292289 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7859. Min Act: -0.1700
Data Index: 2037837 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7234. Min Act: -0.1700
Data Index: 6303957 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7234. Min Act: -0.1700
Data Index: 2061000 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1297. Min Range: -6.1297
Max Act: 5.7547. Min Act: -0.1700
Data Index: 4774295 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19