Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.3998. Min Act: -0.1700
Data Index: 2443587 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.3373. Min Act: -0.1700
Data Index: 3204241 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.3373. Min Act: -0.1700
Data Index: 107747 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.1811. Min Act: -0.1700
Data Index: 6965200 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.1811. Min Act: -0.1700
Data Index: 8429614 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.1498. Min Act: -0.1700
Data Index: 7284866 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.1498. Min Act: -0.1700
Data Index: 8580162 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.1498. Min Act: -0.1700
Data Index: 6461868 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.0873. Min Act: -0.1700
Data Index: 8009909 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3998. Min Range: -4.3998
Max Act: 4.0248. Min Act: -0.1700
Data Index: 6086926 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9935. Min Act: -0.1700
Data Index: 2745837 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9935. Min Act: -0.1700
Data Index: 708371 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9935. Min Act: -0.1700
Data Index: 4495245 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9623. Min Act: -0.1700
Data Index: 4799478 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9623. Min Act: -0.1700
Data Index: 8533666 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9623. Min Act: -0.1700
Data Index: 581517 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9623. Min Act: -0.1700
Data Index: 8535249 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9623. Min Act: -0.1700
Data Index: 7013253 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9623. Min Act: -0.1700
Data Index: 6207882 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3998. Min Range: -4.3998
Max Act: 3.9623. Min Act: -0.1700
Data Index: 8330267 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19