Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.9104. Min Act: -0.1700
Data Index: 8738014 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.8792. Min Act: -0.1700
Data Index: 4065788 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.8792. Min Act: -0.1700
Data Index: 5484138 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.8479. Min Act: -0.1700
Data Index: 2750229 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.8479. Min Act: -0.1700
Data Index: 3969513 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.8167. Min Act: -0.1700
Data Index: 747206 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.8167. Min Act: -0.1700
Data Index: 4185024 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.8167. Min Act: -0.1700
Data Index: 990677 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7854. Min Act: -0.1700
Data Index: 4996283 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7854. Min Act: -0.1700
Data Index: 4162137 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7854. Min Act: -0.1700
Data Index: 3809562 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7854. Min Act: -0.1700
Data Index: 583360 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7542. Min Act: -0.1700
Data Index: 2189747 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7542. Min Act: -0.1700
Data Index: 7170480 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7542. Min Act: -0.1700
Data Index: 2365341 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7854. Min Act: -0.1700
Data Index: 618853 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7542. Min Act: -0.1700
Data Index: 6957516 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7542. Min Act: -0.1700
Data Index: 3401461 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7229. Min Act: -0.1700
Data Index: 8586166 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9104. Min Range: -4.9104
Max Act: 4.7229. Min Act: -0.1700
Data Index: 1353656 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19