Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.9224. Min Act: -0.1700
Data Index: 5339098 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.9139. Min Act: -0.1700
Data Index: 5227816 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8884. Min Act: -0.1700
Data Index: 4283235 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8798. Min Act: -0.1700
Data Index: 1556687 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8713. Min Act: -0.1700
Data Index: 1091428 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8542. Min Act: -0.1698
Data Index: 4897920 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8627. Min Act: -0.1699
Data Index: 2277679 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8542. Min Act: -0.1700
Data Index: 437090 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8542. Min Act: -0.1700
Data Index: 3735159 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8542. Min Act: -0.1700
Data Index: 8345708 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8542. Min Act: -0.1700
Data Index: 5648530 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8627. Min Act: -0.1700
Data Index: 7500308 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8627. Min Act: -0.1700
Data Index: 6745957 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8456. Min Act: -0.1700
Data Index: 1949180 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8456. Min Act: -0.1700
Data Index: 8242960 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8284. Min Act: -0.1700
Data Index: 7562523 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8456. Min Act: -0.1700
Data Index: 6205156 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8284. Min Act: -0.1700
Data Index: 172195 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8370. Min Act: -0.1700
Data Index: 2426401 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9224. Min Range: -1.9224
Max Act: 1.8370. Min Act: -0.1700
Data Index: 1937611 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19