Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6122 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.9857. Min Act: -0.1700
Data Index: 8526358 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.9232. Min Act: -0.1700
Data Index: 7852966 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.8295. Min Act: -0.1700
Data Index: 7374529 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.7670. Min Act: -0.1700
Data Index: 509195 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.7982. Min Act: -0.1700
Data Index: 1711331 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.7670. Min Act: -0.1700
Data Index: 260543 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.6420. Min Act: -0.1700
Data Index: 8430183 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.6420. Min Act: -0.1700
Data Index: 7576525 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.6107. Min Act: -0.1700
Data Index: 1265079 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.6107. Min Act: -0.1700
Data Index: 6323650 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.6107. Min Act: -0.1700
Data Index: 6700222 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.5795. Min Act: -0.1700
Data Index: 2951588 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.5795. Min Act: -0.1700
Data Index: 5820705 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.5482. Min Act: -0.1700
Data Index: 3171695 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.5170. Min Act: -0.1700
Data Index: 3784945 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.4545. Min Act: -0.1700
Data Index: 4008915 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.4857. Min Act: -0.1700
Data Index: 7009351 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.4545. Min Act: -0.1700
Data Index: 3348891 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.4545. Min Act: -0.1700
Data Index: 4028761 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9857. Min Range: -7.9857
Max Act: 7.4232. Min Act: -0.1700
Data Index: 8494567 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19