Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.8185. Min Act: -0.1700
Data Index: 1662305 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.2248. Min Act: -0.1700
Data Index: 6197430 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.1622. Min Act: -0.1700
Data Index: 5376098 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.1935. Min Act: -0.1700
Data Index: 5124592 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.1310. Min Act: -0.1700
Data Index: 2068858 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.1310. Min Act: -0.1700
Data Index: 4821879 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0997. Min Act: -0.1700
Data Index: 7112088 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0997. Min Act: -0.1700
Data Index: 3910068 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0997. Min Act: -0.1700
Data Index: 4846227 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0997. Min Act: -0.1700
Data Index: 3312800 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0997. Min Act: -0.1700
Data Index: 6990535 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0997. Min Act: -0.1700
Data Index: 1178501 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0997. Min Act: -0.1700
Data Index: 8147480 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0685. Min Act: -0.1700
Data Index: 7237435 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0685. Min Act: -0.1700
Data Index: 4676188 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0685. Min Act: -0.1700
Data Index: 336103 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0685. Min Act: -0.1700
Data Index: 568505 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0685. Min Act: -0.1700
Data Index: 4291365 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0372. Min Act: -0.1700
Data Index: 5537684 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8185. Min Range: -4.8185
Max Act: 4.0685. Min Act: -0.1700
Data Index: 6102724 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19