Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1228 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2752. Min Range: -9.2752
Max Act: 9.2752. Min Act: -0.1700
Data Index: 879884 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2752. Min Range: -9.2752
Max Act: 9.2127. Min Act: -0.1700
Data Index: 746246 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2752. Min Range: -9.2752
Max Act: 9.1502. Min Act: -0.1700
Data Index: 4862652 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2752. Min Range: -9.2752
Max Act: 9.0877. Min Act: -0.1700
Data Index: 4982289 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.9627. Min Act: -0.1700
Data Index: 6891013 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.9627. Min Act: -0.1700
Data Index: 2951184 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.9627. Min Act: -0.1700
Data Index: 379887 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.9002. Min Act: -0.1700
Data Index: 476453 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.9002. Min Act: -0.1700
Data Index: 882000 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.8377. Min Act: -0.1700
Data Index: 7465357 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.8377. Min Act: -0.1700
Data Index: 6475356 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.8377. Min Act: -0.1700
Data Index: 2554056 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.8377. Min Act: -0.1700
Data Index: 8643790 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.7752. Min Act: -0.1700
Data Index: 1105435 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.7752. Min Act: -0.1700
Data Index: 4839013 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.7752. Min Act: -0.1700
Data Index: 6722236 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.7127. Min Act: -0.1700
Data Index: 3948488 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.7127. Min Act: -0.1700
Data Index: 2525199 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.7127. Min Act: -0.1700
Data Index: 7340553 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2752. Min Range: -9.2752
Max Act: 8.6502. Min Act: -0.1700
Data Index: 6659550 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19