Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1983 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.9665. Min Act: -0.1700
Data Index: 7132462 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.8102. Min Act: -0.1700
Data Index: 1900376 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.8102. Min Act: -0.1700
Data Index: 6722289 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7790. Min Act: -0.1700
Data Index: 2915201 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7790. Min Act: -0.1700
Data Index: 2293612 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7790. Min Act: -0.1700
Data Index: 261911 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7477. Min Act: -0.1700
Data Index: 6022577 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7165. Min Act: -0.1700
Data Index: 7166658 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7165. Min Act: -0.1700
Data Index: 8279286 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7165. Min Act: -0.1700
Data Index: 164397 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7165. Min Act: -0.1700
Data Index: 2415094 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7165. Min Act: -0.1700
Data Index: 3170324 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.6852. Min Act: -0.1700
Data Index: 1680613 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.7165. Min Act: -0.1700
Data Index: 2145494 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.6852. Min Act: -0.1700
Data Index: 1642745 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.6540. Min Act: -0.1700
Data Index: 228251 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.6540. Min Act: -0.1700
Data Index: 1770852 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.6540. Min Act: -0.1700
Data Index: 2755552 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.6540. Min Act: -0.1700
Data Index: 6830082 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9665. Min Range: -5.9665
Max Act: 5.6540. Min Act: -0.1700
Data Index: 4630225 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19