Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3989 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8911. Min Act: -0.1700
Data Index: 5301742 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8911. Min Act: -0.1700
Data Index: 4648725 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7974. Min Act: -0.1700
Data Index: 4826349 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7036. Min Act: -0.1700
Data Index: 5547766 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6099. Min Act: -0.1700
Data Index: 6540305 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6099. Min Act: -0.1700
Data Index: 4697297 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6099. Min Act: -0.1700
Data Index: 8087128 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6099. Min Act: -0.1700
Data Index: 5923403 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 2254646 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 3043408 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5474. Min Act: -0.1700
Data Index: 7427690 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5474. Min Act: -0.1700
Data Index: 1884305 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.4536. Min Act: -0.1700
Data Index: 5902542 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.4849. Min Act: -0.1700
Data Index: 3420595 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.4224. Min Act: -0.1700
Data Index: 4517533 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.3911. Min Act: -0.1700
Data Index: 3347571 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.3599. Min Act: -0.1700
Data Index: 7688399 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.3599. Min Act: -0.1700
Data Index: 4252125 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.3599. Min Act: -0.1700
Data Index: 6668650 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.3286. Min Act: -0.1700
Data Index: 6324599 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19