Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.5752. Min Act: -0.1700
Data Index: 2370943 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.5127. Min Act: -0.1700
Data Index: 832580 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.3877. Min Act: -0.1700
Data Index: 3129443 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.4189. Min Act: -0.1700
Data Index: 3396585 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.4189. Min Act: -0.1700
Data Index: 8462700 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.3564. Min Act: -0.1700
Data Index: 961715 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.3252. Min Act: -0.1700
Data Index: 8469595 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.3252. Min Act: -0.1700
Data Index: 6193127 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2939. Min Act: -0.1700
Data Index: 7549255 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2939. Min Act: -0.1700
Data Index: 1612661 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2939. Min Act: -0.1700
Data Index: 1141372 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2627. Min Act: -0.1700
Data Index: 6569537 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2627. Min Act: -0.1700
Data Index: 6546868 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2627. Min Act: -0.1700
Data Index: 7651025 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2627. Min Act: -0.1700
Data Index: 19664 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2627. Min Act: -0.1700
Data Index: 932750 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2627. Min Act: -0.1700
Data Index: 5674329 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2314. Min Act: -0.1700
Data Index: 1233036 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2314. Min Act: -0.1700
Data Index: 4758506 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5752. Min Range: -6.5752
Max Act: 6.2002. Min Act: -0.1700
Data Index: 311544 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19