Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.9198. Min Act: -0.1700
Data Index: 4007786 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.7948. Min Act: -0.1700
Data Index: 4239816 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.6073. Min Act: -0.1700
Data Index: 2235484 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.5448. Min Act: -0.1700
Data Index: 6950214 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.4823. Min Act: -0.1700
Data Index: 3858464 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.4823. Min Act: -0.1700
Data Index: 4394478 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.4823. Min Act: -0.1700
Data Index: 491621 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.4510. Min Act: -0.1700
Data Index: 4100229 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.4198. Min Act: -0.1700
Data Index: 5294605 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.3573. Min Act: -0.1700
Data Index: 5891054 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.3573. Min Act: -0.1700
Data Index: 4157017 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.3573. Min Act: -0.1700
Data Index: 1703845 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.2948. Min Act: -0.1700
Data Index: 6531484 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.3260. Min Act: -0.1700
Data Index: 1074938 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.2948. Min Act: -0.1700
Data Index: 6346257 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.2948. Min Act: -0.1700
Data Index: 5509313 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.2635. Min Act: -0.1700
Data Index: 3858463 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.2635. Min Act: -0.1700
Data Index: 2848618 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.2635. Min Act: -0.1700
Data Index: 1965105 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9198. Min Range: -7.9198
Max Act: 7.2323. Min Act: -0.1700
Data Index: 1413988 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19