Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8814. Min Act: -0.1700
Data Index: 7734243 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8814. Min Act: -0.1700
Data Index: 5069411 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8814. Min Act: -0.1700
Data Index: 5071456 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8501. Min Act: -0.1700
Data Index: 5270399 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8188. Min Act: -0.1700
Data Index: 4481175 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8345. Min Act: -0.1700
Data Index: 5317158 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8188. Min Act: -0.1700
Data Index: 6385889 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8188. Min Act: -0.1700
Data Index: 4728111 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8032. Min Act: -0.1700
Data Index: 3882067 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8032. Min Act: -0.1700
Data Index: 6335480 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8032. Min Act: -0.1700
Data Index: 8119700 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8032. Min Act: -0.1700
Data Index: 1345828 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7876. Min Act: -0.1700
Data Index: 8712837 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7563. Min Act: -0.1700
Data Index: 6848901 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7876. Min Act: -0.1700
Data Index: 2837846 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7719. Min Act: -0.1700
Data Index: 40364 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7406. Min Act: -0.1700
Data Index: 6422686 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7250. Min Act: -0.1700
Data Index: 4006847 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7094. Min Act: -0.1700
Data Index: 5643287 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7094. Min Act: -0.1700
Data Index: 3970383 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19