Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0290. Min Range: -5.0290
Max Act: 5.0290. Min Act: -0.1700
Data Index: 5034245 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0290. Min Range: -5.0290
Max Act: 5.0290. Min Act: -0.1700
Data Index: 2930502 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.9977. Min Act: -0.1700
Data Index: 1645645 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.9665. Min Act: -0.1700
Data Index: 1510885 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.9665. Min Act: -0.1700
Data Index: 5579629 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.9352. Min Act: -0.1700
Data Index: 3439929 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8727. Min Act: -0.1700
Data Index: 3729241 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.9040. Min Act: -0.1700
Data Index: 8446331 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8727. Min Act: -0.1700
Data Index: 6347275 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8415. Min Act: -0.1700
Data Index: 7911805 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8415. Min Act: -0.1700
Data Index: 6751165 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8727. Min Act: -0.1700
Data Index: 3528919 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8102. Min Act: -0.1700
Data Index: 922646 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7790. Min Act: -0.1700
Data Index: 3224228 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7790. Min Act: -0.1700
Data Index: 8439182 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7165. Min Act: -0.1700
Data Index: 8130036 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7165. Min Act: -0.1700
Data Index: 4973664 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6540. Min Act: -0.1700
Data Index: 6680845 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6540. Min Act: -0.1700
Data Index: 1269727 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6540. Min Act: -0.1700
Data Index: 3136292 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19