Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3022. Min Range: -5.3022
Max Act: 5.3022. Min Act: -0.1700
Data Index: 2699825 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3022. Min Range: -5.3022
Max Act: 5.1772. Min Act: -0.1700
Data Index: 4412135 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3022. Min Range: -5.3022
Max Act: 5.1147. Min Act: -0.1700
Data Index: 1824425 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3022. Min Range: -5.3022
Max Act: 5.0209. Min Act: -0.1700
Data Index: 5844216 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.9584. Min Act: -0.1700
Data Index: 7978727 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.9897. Min Act: -0.1700
Data Index: 3561524 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.9584. Min Act: -0.1700
Data Index: 6678296 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.9584. Min Act: -0.1700
Data Index: 5786673 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.9272. Min Act: -0.1700
Data Index: 7894928 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.9272. Min Act: -0.1700
Data Index: 4870153 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8959. Min Act: -0.1700
Data Index: 559924 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8959. Min Act: -0.1700
Data Index: 4021754 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8647. Min Act: -0.1700
Data Index: 4668770 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8647. Min Act: -0.1700
Data Index: 3413000 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8334. Min Act: -0.1700
Data Index: 4173927 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8334. Min Act: -0.1700
Data Index: 6906512 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8334. Min Act: -0.1700
Data Index: 5909151 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.7709. Min Act: -0.1700
Data Index: 5802421 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.7709. Min Act: -0.1700
Data Index: 938276 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3022. Min Range: -5.3022
Max Act: 4.8022. Min Act: -0.1700
Data Index: 7439962 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19