Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 949 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3675. Min Range: -4.3675
Max Act: 4.3675. Min Act: -0.1700
Data Index: 8201104 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3675. Min Range: -4.3675
Max Act: 4.2425. Min Act: -0.1700
Data Index: 4962309 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3675. Min Range: -4.3675
Max Act: 4.1175. Min Act: -0.1700
Data Index: 352033 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3675. Min Range: -4.3675
Max Act: 4.0237. Min Act: -0.1700
Data Index: 8801560 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3675. Min Range: -4.3675
Max Act: 4.0237. Min Act: -0.1700
Data Index: 5396312 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3675. Min Range: -4.3675
Max Act: 4.0237. Min Act: -0.1700
Data Index: 2598584 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9924. Min Act: -0.1700
Data Index: 251655 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9612. Min Act: -0.1700
Data Index: 147332 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9612. Min Act: -0.1700
Data Index: 4618887 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9612. Min Act: -0.1700
Data Index: 5396314 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9612. Min Act: -0.1700
Data Index: 6348460 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9924. Min Act: -0.1700
Data Index: 8319594 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9299. Min Act: -0.1700
Data Index: 8132280 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.9299. Min Act: -0.1700
Data Index: 8631622 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.8987. Min Act: -0.1700
Data Index: 7769022 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.8987. Min Act: -0.1700
Data Index: 1693529 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.8987. Min Act: -0.1700
Data Index: 3327725 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.8361. Min Act: -0.1700
Data Index: 3918787 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.8674. Min Act: -0.1700
Data Index: 4826330 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3675. Min Range: -4.3675
Max Act: 3.8674. Min Act: -0.1700
Data Index: 2627984 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19