Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.8920. Min Act: -0.1699
Data Index: 2704547 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.7982. Min Act: -0.1700
Data Index: 1727039 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.7982. Min Act: -0.1700
Data Index: 752740 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6732. Min Act: -0.1700
Data Index: 4294207 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6732. Min Act: -0.1700
Data Index: 5932997 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6732. Min Act: -0.1700
Data Index: 6755597 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6420. Min Act: -0.1700
Data Index: 433466 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6732. Min Act: -0.1700
Data Index: 1920416 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6732. Min Act: -0.1700
Data Index: 4770894 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.5795. Min Act: -0.1700
Data Index: 4754471 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6107. Min Act: -0.1700
Data Index: 7271430 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6420. Min Act: -0.1700
Data Index: 7195617 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6107. Min Act: -0.1700
Data Index: 964339 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.6107. Min Act: -0.1700
Data Index: 4718395 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.5795. Min Act: -0.1700
Data Index: 8601106 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.5482. Min Act: -0.1700
Data Index: 1744367 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.5795. Min Act: -0.1700
Data Index: 4865308 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.5795. Min Act: -0.1700
Data Index: 8648835 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.5795. Min Act: -0.1700
Data Index: 5113737 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8920. Min Range: -5.8920
Max Act: 5.5482. Min Act: -0.1696
Data Index: 8382851 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19