Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.4820. Min Act: -0.1700
Data Index: 2405032 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.3258. Min Act: -0.1700
Data Index: 7940412 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.2945. Min Act: -0.1700
Data Index: 3724785 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.2008. Min Act: -0.1700
Data Index: 8642442 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.2008. Min Act: -0.1700
Data Index: 649930 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.2008. Min Act: -0.1700
Data Index: 5935129 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.2320. Min Act: -0.1700
Data Index: 2847309 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.2008. Min Act: -0.1700
Data Index: 8609563 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1383. Min Act: -0.1700
Data Index: 2696720 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1383. Min Act: -0.1700
Data Index: 4004303 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1383. Min Act: -0.1700
Data Index: 1965921 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1383. Min Act: -0.1700
Data Index: 4751684 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1070. Min Act: -0.1700
Data Index: 7666821 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1070. Min Act: -0.1700
Data Index: 1674239 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1070. Min Act: -0.1700
Data Index: 7289429 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1070. Min Act: -0.1700
Data Index: 3811473 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.1070. Min Act: -0.1700
Data Index: 2825640 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.0758. Min Act: -0.1700
Data Index: 2250704 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.0758. Min Act: -0.1700
Data Index: 7095479 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4820. Min Range: -5.4820
Max Act: 5.0758. Min Act: -0.1700
Data Index: 241285 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19