Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9899. Min Range: -8.9899
Max Act: 8.9899. Min Act: -0.1700
Data Index: 3193240 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9899. Min Range: -8.9899
Max Act: 8.4899. Min Act: -0.1700
Data Index: 8413156 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9899. Min Range: -8.9899
Max Act: 8.4274. Min Act: -0.1700
Data Index: 4688016 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9899. Min Range: -8.9899
Max Act: 8.1149. Min Act: -0.1700
Data Index: 1522625 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9899. Min Range: -8.9899
Max Act: 8.1149. Min Act: -0.1700
Data Index: 5444760 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9899. Min Range: -8.9899
Max Act: 8.1149. Min Act: -0.1700
Data Index: 7510937 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9899. Min Range: -8.9899
Max Act: 8.0524. Min Act: -0.1700
Data Index: 1689835 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.9899. Min Act: -0.1700
Data Index: 3483475 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.9586. Min Act: -0.1700
Data Index: 508286 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.9274. Min Act: -0.1700
Data Index: 3076621 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.9274. Min Act: -0.1700
Data Index: 6331121 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8961. Min Act: -0.1700
Data Index: 3443782 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8649. Min Act: -0.1700
Data Index: 8140898 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8961. Min Act: -0.1700
Data Index: 3946524 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8024. Min Act: -0.1700
Data Index: 2128337 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8336. Min Act: -0.1700
Data Index: 2580933 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8961. Min Act: -0.1700
Data Index: 3676129 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8024. Min Act: -0.1700
Data Index: 2216881 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8336. Min Act: -0.1700
Data Index: 7759980 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9899. Min Range: -8.9899
Max Act: 7.8649. Min Act: -0.1700
Data Index: 2049901 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19