Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5478 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1755. Min Act: -0.1700
Data Index: 4393420 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1443. Min Act: -0.1700
Data Index: 1207864 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.0193. Min Act: -0.1700
Data Index: 8391651 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9255. Min Act: -0.1700
Data Index: 4467809 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 5016751 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 2433354 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8318. Min Act: -0.1700
Data Index: 5356733 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 6696606 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 7795717 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7693. Min Act: -0.1700
Data Index: 2651296 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 5196003 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 4947691 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 2985326 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7068. Min Act: -0.1700
Data Index: 3264965 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7068. Min Act: -0.1700
Data Index: 2157050 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7068. Min Act: -0.1700
Data Index: 7623356 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6755. Min Act: -0.1700
Data Index: 2692754 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6755. Min Act: -0.1700
Data Index: 8307133 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5596439 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.6443. Min Act: -0.1700
Data Index: 7103646 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19