Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5594 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0846. Min Range: -8.0846
Max Act: 8.0846. Min Act: -0.1700
Data Index: 3241177 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0846. Min Range: -8.0846
Max Act: 8.0846. Min Act: -0.1700
Data Index: 7868799 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.8346. Min Act: -0.1700
Data Index: 3553397 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.6159. Min Act: -0.1700
Data Index: 8505226 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.5221. Min Act: -0.1700
Data Index: 926808 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.4909. Min Act: -0.1700
Data Index: 2360646 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.3659. Min Act: -0.1700
Data Index: 7814543 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.3659. Min Act: -0.1700
Data Index: 6629711 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.3034. Min Act: -0.1700
Data Index: 3454838 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.3034. Min Act: -0.1700
Data Index: 4426701 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.2409. Min Act: -0.1700
Data Index: 2377107 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.2096. Min Act: -0.1700
Data Index: 3710194 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.1784. Min Act: -0.1700
Data Index: 1998457 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.1784. Min Act: -0.1700
Data Index: 8624480 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.1471. Min Act: -0.1700
Data Index: 2610574 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.0846. Min Act: -0.1700
Data Index: 7994624 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.1159. Min Act: -0.1700
Data Index: 8298673 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.1159. Min Act: -0.1700
Data Index: 2807314 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.0846. Min Act: -0.1700
Data Index: 8229708 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0846. Min Range: -8.0846
Max Act: 7.0846. Min Act: -0.1700
Data Index: 6884193 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19