Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1243. Min Range: -5.1243
Max Act: 5.1243. Min Act: -0.1700
Data Index: 4317419 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.9993. Min Act: -0.1700
Data Index: 6255807 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.9993. Min Act: -0.1700
Data Index: 8428956 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.9680. Min Act: -0.1700
Data Index: 8495924 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.9055. Min Act: -0.1700
Data Index: 5921980 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.9680. Min Act: -0.1700
Data Index: 6372779 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.9055. Min Act: -0.1700
Data Index: 6493508 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.8118. Min Act: -0.1700
Data Index: 6790474 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.8430. Min Act: -0.1700
Data Index: 2772834 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.8430. Min Act: -0.1700
Data Index: 5050167 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.8118. Min Act: -0.1700
Data Index: 6310918 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7805. Min Act: -0.1700
Data Index: 1533197 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7805. Min Act: -0.1700
Data Index: 2809671 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7805. Min Act: -0.1700
Data Index: 2809683 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7493. Min Act: -0.1700
Data Index: 5173919 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7493. Min Act: -0.1700
Data Index: 8057636 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7493. Min Act: -0.1700
Data Index: 7308040 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7180. Min Act: -0.1700
Data Index: 2381737 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7180. Min Act: -0.1700
Data Index: 277071 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1243. Min Range: -5.1243
Max Act: 4.7180. Min Act: -0.1700
Data Index: 3876200 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19