Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3312. Min Range: -6.3312
Max Act: 6.3312. Min Act: -0.1700
Data Index: 5331034 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3312. Min Range: -6.3312
Max Act: 6.0812. Min Act: -0.1700
Data Index: 4516417 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3312. Min Range: -6.3312
Max Act: 6.0812. Min Act: -0.1700
Data Index: 4110749 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3312. Min Range: -6.3312
Max Act: 6.0500. Min Act: -0.1700
Data Index: 6686628 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3312. Min Range: -6.3312
Max Act: 6.0812. Min Act: -0.1700
Data Index: 2316924 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3312. Min Range: -6.3312
Max Act: 6.0187. Min Act: -0.1700
Data Index: 1693524 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.9875. Min Act: -0.1700
Data Index: 4176270 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.9875. Min Act: -0.1700
Data Index: 2591856 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.9562. Min Act: -0.1700
Data Index: 3782011 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.8937. Min Act: -0.1700
Data Index: 4554049 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.8625. Min Act: -0.1700
Data Index: 5722476 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.8312. Min Act: -0.1700
Data Index: 2226686 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.8312. Min Act: -0.1700
Data Index: 5586975 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.7687. Min Act: -0.1700
Data Index: 4902643 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.7687. Min Act: -0.1700
Data Index: 6031320 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.7687. Min Act: -0.1700
Data Index: 6245333 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.7687. Min Act: -0.1700
Data Index: 4902640 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.7687. Min Act: -0.1700
Data Index: 4902644 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.7062. Min Act: -0.1700
Data Index: 4902637 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3312. Min Range: -6.3312
Max Act: 5.7062. Min Act: -0.1700
Data Index: 4902641 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19