Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4737 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.5614. Min Act: -0.1700
Data Index: 7371535 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.5302. Min Act: -0.1700
Data Index: 7691151 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4677. Min Act: -0.1700
Data Index: 471758 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4677. Min Act: -0.1700
Data Index: 7403742 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4364. Min Act: -0.1700
Data Index: 3935142 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4052. Min Act: -0.1700
Data Index: 6906778 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4052. Min Act: -0.1700
Data Index: 57245 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3739. Min Act: -0.1700
Data Index: 264834 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4052. Min Act: -0.1700
Data Index: 2847256 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3739. Min Act: -0.1699
Data Index: 7920258 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3427. Min Act: -0.1700
Data Index: 865241 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3427. Min Act: -0.1700
Data Index: 4782888 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 1295293 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 2904174 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 4505147 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 8575842 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 8020335 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2802. Min Act: -0.1700
Data Index: 4975538 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2802. Min Act: -0.1700
Data Index: 5827363 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 101590 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19