Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.8631. Min Act: -0.1700
Data Index: 832648 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.8631. Min Act: -0.1700
Data Index: 2118054 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.8319. Min Act: -0.1700
Data Index: 7423746 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7694. Min Act: -0.1700
Data Index: 3790750 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7694. Min Act: -0.1700
Data Index: 2118053 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7694. Min Act: -0.1700
Data Index: 6555044 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7381. Min Act: -0.1700
Data Index: 8081416 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7381. Min Act: -0.1700
Data Index: 302823 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7381. Min Act: -0.1699
Data Index: 4843496 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7381. Min Act: -0.1700
Data Index: 7713960 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7694. Min Act: -0.1700
Data Index: 998038 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7069. Min Act: -0.1700
Data Index: 7140541 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7069. Min Act: -0.1696
Data Index: 867919 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.6756. Min Act: -0.1698
Data Index: 1083939 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7069. Min Act: -0.1700
Data Index: 7996101 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.7069. Min Act: -0.1700
Data Index: 5513770 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.6756. Min Act: -0.1700
Data Index: 4588286 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.6756. Min Act: -0.1700
Data Index: 5168558 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.6756. Min Act: -0.1700
Data Index: 3747536 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8631. Min Range: -5.8631
Max Act: 5.6444. Min Act: -0.1700
Data Index: 7702147 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19