Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.7866. Min Act: -0.1700
Data Index: 7604684 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.7554. Min Act: -0.1700
Data Index: 2789998 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.7241. Min Act: -0.1700
Data Index: 8242620 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.7241. Min Act: -0.1700
Data Index: 2884416 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.6616. Min Act: -0.1700
Data Index: 7672387 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.6616. Min Act: -0.1700
Data Index: 1092264 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.6616. Min Act: -0.1700
Data Index: 8807532 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.6304. Min Act: -0.1700
Data Index: 3965924 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.6304. Min Act: -0.1700
Data Index: 3321073 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.5679. Min Act: -0.1700
Data Index: 1126419 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.5054. Min Act: -0.1700
Data Index: 2633616 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.5054. Min Act: -0.1700
Data Index: 3622330 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.5054. Min Act: -0.1700
Data Index: 8405074 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.4741. Min Act: -0.1700
Data Index: 6895313 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.4429. Min Act: -0.1700
Data Index: 2676405 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.4429. Min Act: -0.1700
Data Index: 8762784 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.4429. Min Act: -0.1700
Data Index: 3480093 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.4741. Min Act: -0.1700
Data Index: 1073778 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.3804. Min Act: -0.1700
Data Index: 6023828 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7866. Min Range: -5.7866
Max Act: 5.4116. Min Act: -0.1700
Data Index: 1285595 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19