Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4380 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.9893. Min Act: -0.1700
Data Index: 1495384 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.9268. Min Act: -0.1700
Data Index: 7865216 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.8330. Min Act: -0.1700
Data Index: 8636937 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.7393. Min Act: -0.1700
Data Index: 7628773 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.7080. Min Act: -0.1700
Data Index: 2716167 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.6455. Min Act: -0.1700
Data Index: 7786705 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5830. Min Act: -0.1700
Data Index: 2924941 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5830. Min Act: -0.1700
Data Index: 3461861 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5830. Min Act: -0.1700
Data Index: 5071712 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5518. Min Act: -0.1700
Data Index: 3352725 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5830. Min Act: -0.1700
Data Index: 3472769 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5518. Min Act: -0.1700
Data Index: 713137 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5518. Min Act: -0.1700
Data Index: 2782672 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5205. Min Act: -0.1700
Data Index: 1151051 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.5205. Min Act: -0.1700
Data Index: 6923732 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.4893. Min Act: -0.1700
Data Index: 6096365 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.4893. Min Act: -0.1700
Data Index: 68395 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.4893. Min Act: -0.1700
Data Index: 7417062 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.4580. Min Act: -0.1700
Data Index: 1560621 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9893. Min Range: -5.9893
Max Act: 5.4580. Min Act: -0.1700
Data Index: 1085189 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19