Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4982019 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.4785. Min Act: -0.1700
Data Index: 1074752 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3848. Min Act: -0.1700
Data Index: 4499030 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3223. Min Act: -0.1700
Data Index: 3763790 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2598. Min Act: -0.1700
Data Index: 1807333 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2598. Min Act: -0.1700
Data Index: 4928948 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2285. Min Act: -0.1700
Data Index: 4570414 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.1973. Min Act: -0.1700
Data Index: 8627631 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.1660. Min Act: -0.1700
Data Index: 8470803 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.1660. Min Act: -0.1700
Data Index: 3940824 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.1348. Min Act: -0.1700
Data Index: 1954959 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0723. Min Act: -0.1700
Data Index: 3132434 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0098. Min Act: -0.1700
Data Index: 127562 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0098. Min Act: -0.1700
Data Index: 6770033 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0410. Min Act: -0.1700
Data Index: 1620438 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0410. Min Act: -0.1700
Data Index: 1744131 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0410. Min Act: -0.1700
Data Index: 4688640 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7285. Min Range: -5.7285
Max Act: 4.9785. Min Act: -0.1700
Data Index: 552070 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0098. Min Act: -0.1700
Data Index: 5827386 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.0410. Min Act: -0.1700
Data Index: 7025060 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19