Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.7067. Min Act: -0.1700
Data Index: 1444068 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.7067. Min Act: -0.1700
Data Index: 184147 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.6755. Min Act: -0.1700
Data Index: 6539562 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.6442. Min Act: -0.1700
Data Index: 2227623 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.5817. Min Act: -0.1700
Data Index: 1389130 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.5505. Min Act: -0.1700
Data Index: 8289011 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.5505. Min Act: -0.1700
Data Index: 4828017 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.5505. Min Act: -0.1700
Data Index: 6502230 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.4880. Min Act: -0.1700
Data Index: 2650927 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.5192. Min Act: -0.1700
Data Index: 3870532 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.4880. Min Act: -0.1700
Data Index: 276783 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.4880. Min Act: -0.1700
Data Index: 8085530 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.4255. Min Act: -0.1700
Data Index: 1336840 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.3630. Min Act: -0.1700
Data Index: 1041905 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.4255. Min Act: -0.1700
Data Index: 6235817 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.3942. Min Act: -0.1700
Data Index: 3702901 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.3630. Min Act: -0.1700
Data Index: 6237987 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.3630. Min Act: -0.1700
Data Index: 5857343 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.3317. Min Act: -0.1700
Data Index: 1652465 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7067. Min Range: -5.7067
Max Act: 5.2692. Min Act: -0.1700
Data Index: 5300044 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19