Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.6755. Min Act: -0.1700
Data Index: 8079219 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.6755. Min Act: -0.1700
Data Index: 1358974 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.5817. Min Act: -0.1700
Data Index: 4992581 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.5817. Min Act: -0.1700
Data Index: 3645595 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.5505. Min Act: -0.1700
Data Index: 542830 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1418069 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.4567. Min Act: -0.1700
Data Index: 8191770 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.4255. Min Act: -0.1700
Data Index: 2490638 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.4567. Min Act: -0.1700
Data Index: 6599293 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3942. Min Act: -0.1700
Data Index: 4992577 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3942. Min Act: -0.1700
Data Index: 1756319 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3942. Min Act: -0.1700
Data Index: 4992573 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3630. Min Act: -0.1700
Data Index: 677148 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3942. Min Act: -0.1700
Data Index: 3641302 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3630. Min Act: -0.1700
Data Index: 8229983 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3317. Min Act: -0.1700
Data Index: 8079214 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3005. Min Act: -0.1700
Data Index: 3375876 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3630. Min Act: -0.1700
Data Index: 2795851 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3317. Min Act: -0.1700
Data Index: 2163613 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6755. Min Range: -5.6755
Max Act: 5.3005. Min Act: -0.1700
Data Index: 6636172 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19