Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.8765. Min Act: -0.1700
Data Index: 5335829 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.9078. Min Act: -0.1700
Data Index: 8779819 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.8140. Min Act: -0.1700
Data Index: 4447089 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.8140. Min Act: -0.1700
Data Index: 1693871 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.8140. Min Act: -0.1700
Data Index: 7351370 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7828. Min Act: -0.1700
Data Index: 4966942 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7828. Min Act: -0.1700
Data Index: 4369491 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7515. Min Act: -0.1700
Data Index: 8080194 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7515. Min Act: -0.1690
Data Index: 536418 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7515. Min Act: -0.1700
Data Index: 3344682 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7515. Min Act: -0.1700
Data Index: 4161997 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7515. Min Act: -0.1700
Data Index: 141535 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7203. Min Act: -0.1699
Data Index: 3713969 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.7203. Min Act: -0.1700
Data Index: 5813938 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.6890. Min Act: -0.1700
Data Index: 694367 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.6890. Min Act: -0.1700
Data Index: 3706216 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.6890. Min Act: -0.1700
Data Index: 1480171 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.6890. Min Act: -0.1700
Data Index: 779917 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.6890. Min Act: -0.1698
Data Index: 4091669 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.6578. Min Act: -0.1700
Data Index: 4438921 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19