Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1448 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.9272. Min Act: -0.1700
Data Index: 2239577 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.8022. Min Act: -0.1700
Data Index: 7102773 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.8022. Min Act: -0.1700
Data Index: 4259454 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.7397. Min Act: -0.1700
Data Index: 4470445 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.7397. Min Act: -0.1700
Data Index: 7264023 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.6772. Min Act: -0.1700
Data Index: 2795630 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.5522. Min Act: -0.1700
Data Index: 551491 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.5522. Min Act: -0.1700
Data Index: 782709 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.4272. Min Act: -0.1700
Data Index: 6666253 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.4272. Min Act: -0.1700
Data Index: 7149985 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.4272. Min Act: -0.1700
Data Index: 7635159 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.2397. Min Act: -0.1700
Data Index: 7102772 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.2709. Min Act: -0.1700
Data Index: 1429890 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.2709. Min Act: -0.1700
Data Index: 3775837 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.2709. Min Act: -0.1700
Data Index: 1466501 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.2084. Min Act: -0.1700
Data Index: 7342043 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.2084. Min Act: -0.1700
Data Index: 3414787 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.2084. Min Act: -0.1700
Data Index: 6453978 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.1772. Min Act: -0.1700
Data Index: 7381338 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9272. Min Range: -8.9272
Max Act: 8.1772. Min Act: -0.1700
Data Index: 6771916 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19