Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.5013. Min Act: -0.1700
Data Index: 5795337 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.3451. Min Act: -0.1700
Data Index: 2186131 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.3138. Min Act: -0.1700
Data Index: 5795335 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.2826. Min Act: -0.1700
Data Index: 7955564 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.2513. Min Act: -0.1700
Data Index: 2645200 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.2513. Min Act: -0.1700
Data Index: 2650275 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.2201. Min Act: -0.1700
Data Index: 7727316 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.1888. Min Act: -0.1700
Data Index: 431555 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.1576. Min Act: -0.1700
Data Index: 3428624 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.1576. Min Act: -0.1700
Data Index: 1614081 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.1576. Min Act: -0.1700
Data Index: 7738489 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.0951. Min Act: -0.1700
Data Index: 399026 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.1263. Min Act: -0.1700
Data Index: 5941816 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.0951. Min Act: -0.1700
Data Index: 1037675 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.1263. Min Act: -0.1700
Data Index: 7931307 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.0951. Min Act: -0.1700
Data Index: 2817480 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.0638. Min Act: -0.1700
Data Index: 501698 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.0638. Min Act: -0.1700
Data Index: 6690648 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.0951. Min Act: -0.1700
Data Index: 6133473 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5013. Min Range: -5.5013
Max Act: 5.0951. Min Act: -0.1700
Data Index: 4393460 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19