Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4569 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.1735. Min Act: -0.1700
Data Index: 329792 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.1263. Min Act: -0.1700
Data Index: 1688524 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0948. Min Act: -0.1700
Data Index: 4478557 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0790. Min Act: -0.1700
Data Index: 7085265 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0632. Min Act: -0.1700
Data Index: 2421246 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0475. Min Act: -0.1700
Data Index: 7988845 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0317. Min Act: -0.1700
Data Index: 6753965 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0159. Min Act: -0.1700
Data Index: 6077362 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0001. Min Act: -0.1700
Data Index: 3265102 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1735. Min Range: -3.1735
Max Act: 3.0001. Min Act: -0.1700
Data Index: 1956065 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9843. Min Act: -0.1700
Data Index: 7658598 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9843. Min Act: -0.1700
Data Index: 3759471 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9685. Min Act: -0.1700
Data Index: 2330832 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9685. Min Act: -0.1700
Data Index: 5817959 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9526. Min Act: -0.1700
Data Index: 2867597 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9526. Min Act: -0.1700
Data Index: 8728588 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9526. Min Act: -0.1700
Data Index: 4742379 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9368. Min Act: -0.1700
Data Index: 6209276 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9210. Min Act: -0.1700
Data Index: 2189610 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1735. Min Range: -3.1735
Max Act: 2.9368. Min Act: -0.1700
Data Index: 5164508 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19