Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1660. Min Act: -0.1700
Data Index: 573071 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1347. Min Act: -0.1700
Data Index: 3001526 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1347. Min Act: -0.1700
Data Index: 3493833 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1347. Min Act: -0.1700
Data Index: 3633219 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1347. Min Act: -0.1700
Data Index: 4309125 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 1138831 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 7182108 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 3373740 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 4864439 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 634366 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 2253794 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 4809133 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 2556062 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 2144541 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0722. Min Act: -0.1700
Data Index: 8095370 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0722. Min Act: -0.1700
Data Index: 2363824 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0722. Min Act: -0.1700
Data Index: 1813849 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0722. Min Act: -0.1700
Data Index: 1180190 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.1034. Min Act: -0.1700
Data Index: 6616081 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1660. Min Range: -4.1660
Max Act: 4.0409. Min Act: -0.1700
Data Index: 8039970 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19