Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1034. Min Range: -2.1034
Max Act: 2.1034. Min Act: -0.1700
Data Index: 7462728 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1034. Min Range: -2.1034
Max Act: 2.0866. Min Act: -0.1700
Data Index: 6045181 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1034. Min Range: -2.1034
Max Act: 2.0194. Min Act: -0.1700
Data Index: 663753 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1034. Min Range: -2.1034
Max Act: 2.0194. Min Act: -0.1700
Data Index: 1313528 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1034. Min Range: -2.1034
Max Act: 2.0025. Min Act: -0.1700
Data Index: 3850991 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1034. Min Range: -2.1034
Max Act: 2.0025. Min Act: -0.1700
Data Index: 4553057 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9940. Min Act: -0.1700
Data Index: 523191 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9856. Min Act: -0.1700
Data Index: 5016375 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9856. Min Act: -0.1700
Data Index: 2228341 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9856. Min Act: -0.1700
Data Index: 4553058 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9771. Min Act: -0.1700
Data Index: 7081116 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9686. Min Act: -0.1700
Data Index: 1354458 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9602. Min Act: -0.1700
Data Index: 582056 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9686. Min Act: -0.1700
Data Index: 6297465 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9602. Min Act: -0.1700
Data Index: 5783930 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9602. Min Act: -0.1700
Data Index: 5973709 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9432. Min Act: -0.1700
Data Index: 7462732 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9432. Min Act: -0.1700
Data Index: 1566025 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9262. Min Act: -0.1700
Data Index: 7194340 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1034. Min Range: -2.1034
Max Act: 1.9347. Min Act: -0.1700
Data Index: 2847009 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19