Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.2522. Min Act: -0.1700
Data Index: 5802377 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.1897. Min Act: -0.1700
Data Index: 2776926 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.1897. Min Act: -0.1700
Data Index: 5709210 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.1897. Min Act: -0.1700
Data Index: 5802379 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.1584. Min Act: -0.1700
Data Index: 2776927 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.0959. Min Act: -0.1700
Data Index: 5802380 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.0022. Min Act: -0.1700
Data Index: 3245188 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2522. Min Range: -6.2522
Max Act: 6.0022. Min Act: -0.1700
Data Index: 5802378 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.9709. Min Act: -0.1700
Data Index: 3730249 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.9084. Min Act: -0.1700
Data Index: 5454461 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.8772. Min Act: -0.1700
Data Index: 3670236 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.8772. Min Act: -0.1700
Data Index: 5802381 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.8459. Min Act: -0.1700
Data Index: 5946886 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5946887 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5952745 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.7834. Min Act: -0.1700
Data Index: 4275829 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.7522. Min Act: -0.1700
Data Index: 1054622 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.7522. Min Act: -0.1700
Data Index: 246685 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.7834. Min Act: -0.1700
Data Index: 2212736 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2522. Min Range: -6.2522
Max Act: 5.7834. Min Act: -0.1700
Data Index: 7719007 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19