Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5322 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.4902. Min Act: -0.1700
Data Index: 6770980 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.2715. Min Act: -0.1700
Data Index: 3187826 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.3027. Min Act: -0.1700
Data Index: 2368286 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.1465. Min Act: -0.1700
Data Index: 8632485 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.1465. Min Act: -0.1700
Data Index: 4278235 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.0840. Min Act: -0.1700
Data Index: 471264 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.1152. Min Act: -0.1700
Data Index: 1670017 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.0840. Min Act: -0.1700
Data Index: 4103155 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4902. Min Range: -7.4902
Max Act: 7.0527. Min Act: -0.1700
Data Index: 8528340 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.9902. Min Act: -0.1700
Data Index: 3215286 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.9277. Min Act: -0.1700
Data Index: 8311627 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.8965. Min Act: -0.1700
Data Index: 5543338 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.8027. Min Act: -0.1700
Data Index: 8592835 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.8027. Min Act: -0.1700
Data Index: 8475109 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.8027. Min Act: -0.1700
Data Index: 1220365 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.8027. Min Act: -0.1700
Data Index: 6835249 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.8027. Min Act: -0.1700
Data Index: 3531451 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.7402. Min Act: -0.1700
Data Index: 8077466 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.7715. Min Act: -0.1700
Data Index: 1350975 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4902. Min Range: -7.4902
Max Act: 6.7090. Min Act: -0.1700
Data Index: 4751032 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19