Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5670 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.3317. Min Act: -0.1700
Data Index: 200678 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.3005. Min Act: -0.1700
Data Index: 2861228 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.3005. Min Act: -0.1700
Data Index: 4161242 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.2692. Min Act: -0.1700
Data Index: 1847319 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.2692. Min Act: -0.1700
Data Index: 3812268 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.2380. Min Act: -0.1700
Data Index: 2499091 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.2380. Min Act: -0.1700
Data Index: 6590712 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1755. Min Act: -0.1700
Data Index: 394698 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1442. Min Act: -0.1700
Data Index: 1201503 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1442. Min Act: -0.1700
Data Index: 3118685 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1442. Min Act: -0.1700
Data Index: 8501893 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1442. Min Act: -0.1700
Data Index: 6554533 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1442. Min Act: -0.1700
Data Index: 53092 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1442. Min Act: -0.1700
Data Index: 6278412 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1130. Min Act: -0.1700
Data Index: 3874199 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1130. Min Act: -0.1700
Data Index: 695386 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1130. Min Act: -0.1700
Data Index: 6599490 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1130. Min Act: -0.1700
Data Index: 7434306 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.1442. Min Act: -0.1700
Data Index: 3513693 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3317. Min Range: -5.3317
Max Act: 5.0817. Min Act: -0.1700
Data Index: 1028595 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19