Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6288 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.6145. Min Act: -0.1700
Data Index: 5178645 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.4895. Min Act: -0.1700
Data Index: 5516476 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.4583. Min Act: -0.1700
Data Index: 7319550 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.4270. Min Act: -0.1700
Data Index: 1810073 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.4270. Min Act: -0.1700
Data Index: 5873832 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.4270. Min Act: -0.1700
Data Index: 714920 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.3958. Min Act: -0.1700
Data Index: 2366109 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2708. Min Act: -0.1700
Data Index: 7493997 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.3020. Min Act: -0.1700
Data Index: 4084892 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2708. Min Act: -0.1700
Data Index: 5791325 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2395. Min Act: -0.1700
Data Index: 3771210 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2395. Min Act: -0.1700
Data Index: 1831610 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2395. Min Act: -0.1700
Data Index: 2413628 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2083. Min Act: -0.1700
Data Index: 233516 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2083. Min Act: -0.1700
Data Index: 1308481 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2083. Min Act: -0.1700
Data Index: 8006924 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2083. Min Act: -0.1700
Data Index: 1273937 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.2083. Min Act: -0.1700
Data Index: 4296291 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.1770. Min Act: -0.1700
Data Index: 5033231 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6145. Min Range: -7.6145
Max Act: 7.1770. Min Act: -0.1700
Data Index: 2138938 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19