Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.9893. Min Act: -0.1700
Data Index: 3838611 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6456. Min Range: -8.6456
Max Act: 8.6456. Min Act: -0.1700
Data Index: 784904 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.7081. Min Act: -0.1700
Data Index: 924 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5831. Min Act: -0.1700
Data Index: 935416 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5831. Min Act: -0.1700
Data Index: 2709620 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.6456. Min Act: -0.1700
Data Index: 3813785 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5831. Min Act: -0.1700
Data Index: 5941545 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.6143. Min Act: -0.1700
Data Index: 4260043 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.4893. Min Act: -0.1700
Data Index: 4040180 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5831. Min Act: -0.1700
Data Index: 17240 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.4893. Min Act: -0.1700
Data Index: 8546865 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5206. Min Act: -0.1700
Data Index: 7417275 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5831. Min Act: -0.1700
Data Index: 3433466 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5831. Min Act: -0.1700
Data Index: 7765808 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.6143. Min Act: -0.1700
Data Index: 5194200 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5206. Min Act: -0.1700
Data Index: 3409340 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5206. Min Act: -0.1700
Data Index: 3409980 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5206. Min Act: -0.1700
Data Index: 2425607 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.4581. Min Act: -0.1700
Data Index: 968722 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6456. Min Range: -8.6456
Max Act: 7.5518. Min Act: -0.1700
Data Index: 1099767 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19