Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.6145. Min Act: -0.1700
Data Index: 61820 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.6145. Min Act: -0.1700
Data Index: 4831903 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.5832. Min Act: -0.1700
Data Index: 3758403 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.5520. Min Act: -0.1700
Data Index: 2737184 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.5520. Min Act: -0.1700
Data Index: 1014983 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.5207. Min Act: -0.1700
Data Index: 3263305 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.5207. Min Act: -0.1700
Data Index: 1603741 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4582. Min Act: -0.1700
Data Index: 61804 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4582. Min Act: -0.1700
Data Index: 1939794 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4582. Min Act: -0.1700
Data Index: 6126998 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4582. Min Act: -0.1700
Data Index: 591967 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4895. Min Act: -0.1700
Data Index: 8761874 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4582. Min Act: -0.1700
Data Index: 8036788 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4582. Min Act: -0.1700
Data Index: 4824392 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4270. Min Act: -0.1700
Data Index: 2071765 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4270. Min Act: -0.1700
Data Index: 5926250 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.4270. Min Act: -0.1700
Data Index: 3931370 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.3957. Min Act: -0.1700
Data Index: 7712286 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.3645. Min Act: -0.1700
Data Index: 1235695 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6145. Min Range: -6.6145
Max Act: 6.3645. Min Act: -0.1700
Data Index: 4791067 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19