Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5736. Min Range: -7.5736
Max Act: 7.5736. Min Act: -0.1700
Data Index: 7083613 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5736. Min Range: -7.5736
Max Act: 7.4486. Min Act: -0.1699
Data Index: 5307070 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5736. Min Range: -7.5736
Max Act: 7.3548. Min Act: -0.1700
Data Index: 6071538 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5736. Min Range: -7.5736
Max Act: 7.1361. Min Act: -0.1694
Data Index: 5307069 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5736. Min Range: -7.5736
Max Act: 7.1673. Min Act: -0.1700
Data Index: 8655613 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5736. Min Range: -7.5736
Max Act: 7.2298. Min Act: -0.1700
Data Index: 91597 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.9486. Min Act: -0.1700
Data Index: 563537 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.9486. Min Act: -0.1700
Data Index: 4279092 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.9486. Min Act: -0.1700
Data Index: 701363 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8861. Min Act: -0.1700
Data Index: 8453346 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.7611. Min Act: -0.1700
Data Index: 701365 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.9798. Min Act: -0.1700
Data Index: 7995672 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5736. Min Range: -7.5736
Max Act: 7.0111. Min Act: -0.1700
Data Index: 4626745 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8236. Min Act: -0.1699
Data Index: 6987080 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8861. Min Act: -0.1700
Data Index: 770464 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8861. Min Act: -0.1700
Data Index: 6297268 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8861. Min Act: -0.1700
Data Index: 1806483 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8861. Min Act: -0.1700
Data Index: 5848949 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8236. Min Act: -0.1700
Data Index: 8780515 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5736. Min Range: -7.5736
Max Act: 6.8236. Min Act: -0.1700
Data Index: 7371683 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19