Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.5614. Min Act: -0.1700
Data Index: 2837359 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4988. Min Act: -0.1700
Data Index: 5229828 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4831. Min Act: -0.1700
Data Index: 1754512 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4674. Min Act: -0.1700
Data Index: 5820575 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4831. Min Act: -0.1700
Data Index: 7987705 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4518. Min Act: -0.1700
Data Index: 414043 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4518. Min Act: -0.1700
Data Index: 6616012 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4518. Min Act: -0.1700
Data Index: 6274174 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4518. Min Act: -0.1700
Data Index: 559698 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4361. Min Act: -0.1700
Data Index: 7316571 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4361. Min Act: -0.1700
Data Index: 5557223 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4204. Min Act: -0.1700
Data Index: 2769682 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4048. Min Act: -0.1700
Data Index: 5706628 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4204. Min Act: -0.1700
Data Index: 559703 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.4048. Min Act: -0.1700
Data Index: 6252325 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.3891. Min Act: -0.1700
Data Index: 4817026 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.3891. Min Act: -0.1700
Data Index: 980153 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.3734. Min Act: -0.1700
Data Index: 8778934 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.3577. Min Act: -0.1700
Data Index: 8457390 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5614. Min Range: -3.5614
Max Act: 3.3734. Min Act: -0.1700
Data Index: 1665301 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19