Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1062 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0444. Min Range: -7.0444
Max Act: 7.0444. Min Act: -0.1700
Data Index: 8312746 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.9194. Min Act: -0.1700
Data Index: 5497119 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.7631. Min Act: -0.1700
Data Index: 647780 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.6694. Min Act: -0.1700
Data Index: 7180629 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.6381. Min Act: -0.1700
Data Index: 4138919 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.6694. Min Act: -0.1700
Data Index: 5565064 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.6069. Min Act: -0.1700
Data Index: 492311 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.6069. Min Act: -0.1700
Data Index: 8169035 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5444. Min Act: -0.1700
Data Index: 4837515 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5756. Min Act: -0.1700
Data Index: 1479323 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5756. Min Act: -0.1700
Data Index: 7781262 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5444. Min Act: -0.1700
Data Index: 7342237 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5444. Min Act: -0.1700
Data Index: 2402493 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5131. Min Act: -0.1700
Data Index: 5402596 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5131. Min Act: -0.1700
Data Index: 4696984 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5444. Min Act: -0.1700
Data Index: 7988911 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.5131. Min Act: -0.1700
Data Index: 6417259 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.4819. Min Act: -0.1700
Data Index: 120216 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.4819. Min Act: -0.1700
Data Index: 4542944 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0444. Min Range: -7.0444
Max Act: 6.4194. Min Act: -0.1700
Data Index: 1350379 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19