Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.9939. Min Act: -0.1700
Data Index: 1286720 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.9314. Min Act: -0.1700
Data Index: 7066877 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.9001. Min Act: -0.1700
Data Index: 7640778 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1183466 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.8532. Min Act: -0.1700
Data Index: 460154 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.8063. Min Act: -0.1700
Data Index: 7805208 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.7594. Min Act: -0.1700
Data Index: 5910076 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.7594. Min Act: -0.1700
Data Index: 20974 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.7438. Min Act: -0.1700
Data Index: 3082820 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.7125. Min Act: -0.1700
Data Index: 1515842 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.7281. Min Act: -0.1700
Data Index: 8014301 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.7125. Min Act: -0.1700
Data Index: 3936026 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6968. Min Act: -0.1700
Data Index: 4004682 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7850155 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6812. Min Act: -0.1700
Data Index: 5756100 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6812. Min Act: -0.1700
Data Index: 755437 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6499. Min Act: -0.1700
Data Index: 7850156 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6499. Min Act: -0.1700
Data Index: 7919502 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6499. Min Act: -0.1700
Data Index: 1917801 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9939. Min Range: -3.9939
Max Act: 3.6968. Min Act: -0.1700
Data Index: 2549410 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19