Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0364. Min Range: -6.0364
Max Act: 6.0364. Min Act: -0.1700
Data Index: 3533114 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.9426. Min Act: -0.1700
Data Index: 6813569 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.9114. Min Act: -0.1700
Data Index: 396366 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.8489. Min Act: -0.1700
Data Index: 4442181 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.7864. Min Act: -0.1700
Data Index: 3737049 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.7551. Min Act: -0.1700
Data Index: 1906598 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6926. Min Act: -0.1700
Data Index: 6331365 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6926. Min Act: -0.1700
Data Index: 829916 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6926. Min Act: -0.1700
Data Index: 5784543 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6926. Min Act: -0.1700
Data Index: 7548684 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6926. Min Act: -0.1700
Data Index: 2104231 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6301. Min Act: -0.1700
Data Index: 6427731 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6301. Min Act: -0.1700
Data Index: 1199284 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.6301. Min Act: -0.1700
Data Index: 1351722 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.5989. Min Act: -0.1700
Data Index: 983553 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.5989. Min Act: -0.1700
Data Index: 2781683 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.5676. Min Act: -0.1700
Data Index: 3794586 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.5364. Min Act: -0.1700
Data Index: 1608286 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.5364. Min Act: -0.1700
Data Index: 7873477 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0364. Min Range: -6.0364
Max Act: 5.5364. Min Act: -0.1700
Data Index: 281992 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19