Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.9641. Min Act: -0.1700
Data Index: 2114520 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.8391. Min Act: -0.1700
Data Index: 3001329 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.8703. Min Act: -0.1700
Data Index: 6697410 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.8078. Min Act: -0.1700
Data Index: 2147402 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.7453. Min Act: -0.1700
Data Index: 84363 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.6516. Min Act: -0.1700
Data Index: 4126946 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.6203. Min Act: -0.1700
Data Index: 1879574 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5891. Min Act: -0.1700
Data Index: 1148490 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5891. Min Act: -0.1700
Data Index: 7730390 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5891. Min Act: -0.1700
Data Index: 5016164 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5891. Min Act: -0.1700
Data Index: 1124871 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5891. Min Act: -0.1700
Data Index: 6111162 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5578. Min Act: -0.1700
Data Index: 1261910 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5578. Min Act: -0.1700
Data Index: 959923 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5578. Min Act: -0.1700
Data Index: 3368211 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5266. Min Act: -0.1700
Data Index: 3853619 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5578. Min Act: -0.1700
Data Index: 8062286 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5578. Min Act: -0.1700
Data Index: 8104376 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5266. Min Act: -0.1700
Data Index: 1448018 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9641. Min Range: -6.9641
Max Act: 6.5266. Min Act: -0.1700
Data Index: 5348940 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19