Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4583 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0935. Min Range: -5.0935
Max Act: 5.0935. Min Act: -0.1700
Data Index: 1118506 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0935. Min Range: -5.0935
Max Act: 5.0935. Min Act: -0.1700
Data Index: 346721 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0935. Min Range: -5.0935
Max Act: 5.0622. Min Act: -0.1700
Data Index: 53848 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0935. Min Range: -5.0935
Max Act: 5.0310. Min Act: -0.1700
Data Index: 4777905 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.9997. Min Act: -0.1700
Data Index: 6138991 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.9997. Min Act: -0.1700
Data Index: 2549368 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.9685. Min Act: -0.1700
Data Index: 6984605 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.9372. Min Act: -0.1700
Data Index: 877306 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.9685. Min Act: -0.1700
Data Index: 4796225 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.9060. Min Act: -0.1700
Data Index: 8404839 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.9060. Min Act: -0.1700
Data Index: 544655 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.8747. Min Act: -0.1700
Data Index: 4632507 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.8747. Min Act: -0.1700
Data Index: 4215726 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.8122. Min Act: -0.1700
Data Index: 5470251 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.8435. Min Act: -0.1700
Data Index: 1901800 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.8122. Min Act: -0.1700
Data Index: 7914382 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.7810. Min Act: -0.1700
Data Index: 1678782 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.7497. Min Act: -0.1700
Data Index: 3423840 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.7810. Min Act: -0.1700
Data Index: 6536980 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0935. Min Range: -5.0935
Max Act: 4.7810. Min Act: -0.1700
Data Index: 5191168 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19