Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4593 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2922. Min Range: -7.2922
Max Act: 7.2922. Min Act: -0.1700
Data Index: 7329209 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2922. Min Range: -7.2922
Max Act: 7.2297. Min Act: -0.1700
Data Index: 224050 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2922. Min Range: -7.2922
Max Act: 7.0422. Min Act: -0.1700
Data Index: 7927910 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.8234. Min Act: -0.1700
Data Index: 6547044 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.7609. Min Act: -0.1700
Data Index: 5947479 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.7297. Min Act: -0.1700
Data Index: 4225944 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.7297. Min Act: -0.1700
Data Index: 1235568 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.6984. Min Act: -0.1700
Data Index: 7466629 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.6984. Min Act: -0.1700
Data Index: 1457317 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.6672. Min Act: -0.1700
Data Index: 696040 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.6672. Min Act: -0.1700
Data Index: 2549895 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.6359. Min Act: -0.1700
Data Index: 8174614 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.6359. Min Act: -0.1700
Data Index: 7949478 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.5734. Min Act: -0.1700
Data Index: 978752 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.4797. Min Act: -0.1700
Data Index: 7611592 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.4172. Min Act: -0.1700
Data Index: 6651998 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.4172. Min Act: -0.1700
Data Index: 8362248 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.4172. Min Act: -0.1700
Data Index: 7717356 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.4172. Min Act: -0.1700
Data Index: 3054864 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2922. Min Range: -7.2922
Max Act: 6.3859. Min Act: -0.1700
Data Index: 7795230 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19