Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.4734. Min Act: -0.1700
Data Index: 2342983 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.3796. Min Act: -0.1700
Data Index: 8660561 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.3484. Min Act: -0.1700
Data Index: 4354312 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.3484. Min Act: -0.1700
Data Index: 3071377 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.3484. Min Act: -0.1700
Data Index: 5404434 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.3171. Min Act: -0.1700
Data Index: 7152126 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2859. Min Act: -0.1700
Data Index: 5508698 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2859. Min Act: -0.1700
Data Index: 2726797 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2859. Min Act: -0.1700
Data Index: 1760495 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2234. Min Act: -0.1700
Data Index: 7432452 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2546. Min Act: -0.1700
Data Index: 5703365 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2546. Min Act: -0.1700
Data Index: 8023235 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2546. Min Act: -0.1700
Data Index: 8760136 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2234. Min Act: -0.1700
Data Index: 5803963 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2234. Min Act: -0.1700
Data Index: 8493752 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2234. Min Act: -0.1700
Data Index: 8619310 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.2234. Min Act: -0.1700
Data Index: 7785624 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.1921. Min Act: -0.1700
Data Index: 1999832 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.1609. Min Act: -0.1700
Data Index: 390863 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4734. Min Range: -6.4734
Max Act: 6.1296. Min Act: -0.1700
Data Index: 6386176 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19