Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1015 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1909. Min Range: -6.1909
Max Act: 6.1596. Min Act: -0.1700
Data Index: 5375462 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1909. Min Range: -6.1909
Max Act: 6.1909. Min Act: -0.1700
Data Index: 1000997 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1909. Min Range: -6.1909
Max Act: 6.1284. Min Act: -0.1700
Data Index: 1153011 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.9721. Min Act: -0.1700
Data Index: 4796247 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.9721. Min Act: -0.1700
Data Index: 3094216 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.9721. Min Act: -0.1700
Data Index: 2020495 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.9409. Min Act: -0.1700
Data Index: 6548015 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8784. Min Act: -0.1700
Data Index: 5449457 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8784. Min Act: -0.1700
Data Index: 8807816 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8784. Min Act: -0.1700
Data Index: 2464314 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8471. Min Act: -0.1700
Data Index: 14611 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8471. Min Act: -0.1700
Data Index: 1654934 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.7846. Min Act: -0.1700
Data Index: 8305803 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8159. Min Act: -0.1700
Data Index: 2594723 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8159. Min Act: -0.1700
Data Index: 3631400 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8159. Min Act: -0.1700
Data Index: 5176075 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.7846. Min Act: -0.1700
Data Index: 6436844 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.7534. Min Act: -0.1700
Data Index: 1756206 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.8159. Min Act: -0.1700
Data Index: 2014124 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1909. Min Range: -6.1909
Max Act: 5.7846. Min Act: -0.1700
Data Index: 1629502 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19