Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4395 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6783. Min Range: -8.6783
Max Act: 8.6783. Min Act: -0.1700
Data Index: 2618102 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6783. Min Range: -8.6783
Max Act: 8.2095. Min Act: -0.1700
Data Index: 5552200 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6783. Min Range: -8.6783
Max Act: 8.1783. Min Act: -0.1700
Data Index: 2521481 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6783. Min Range: -8.6783
Max Act: 8.1158. Min Act: -0.1700
Data Index: 1501150 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6783. Min Range: -8.6783
Max Act: 8.0533. Min Act: -0.1700
Data Index: 3456573 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.9908. Min Act: -0.1700
Data Index: 913056 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.8658. Min Act: -0.1700
Data Index: 7321707 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.8345. Min Act: -0.1700
Data Index: 2075261 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.8345. Min Act: -0.1700
Data Index: 3181625 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.7720. Min Act: -0.1700
Data Index: 4124923 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.7408. Min Act: -0.1700
Data Index: 5790849 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.7408. Min Act: -0.1700
Data Index: 5845404 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.7408. Min Act: -0.1700
Data Index: 1754805 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.7408. Min Act: -0.1700
Data Index: 4124925 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.7095. Min Act: -0.1700
Data Index: 390201 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.6470. Min Act: -0.1700
Data Index: 5098938 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.6158. Min Act: -0.1700
Data Index: 5707817 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.6158. Min Act: -0.1700
Data Index: 6618718 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.5845. Min Act: -0.1700
Data Index: 8026224 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6783. Min Range: -8.6783
Max Act: 7.4908. Min Act: -0.1700
Data Index: 6370219 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19