Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.6211. Min Act: -0.1700
Data Index: 4952532 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.6211. Min Act: -0.1700
Data Index: 4953971 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.5273. Min Act: -0.1700
Data Index: 981822 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4961. Min Act: -0.1700
Data Index: 2280327 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4648. Min Act: -0.1700
Data Index: 1102557 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4648. Min Act: -0.1700
Data Index: 2015708 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4648. Min Act: -0.1700
Data Index: 7546068 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4648. Min Act: -0.1700
Data Index: 7977026 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4648. Min Act: -0.1700
Data Index: 6079722 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4336. Min Act: -0.1700
Data Index: 7244261 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4336. Min Act: -0.1700
Data Index: 8050229 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4336. Min Act: -0.1700
Data Index: 7080065 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4023. Min Act: -0.1700
Data Index: 3750329 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4023. Min Act: -0.1700
Data Index: 1038780 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.4023. Min Act: -0.1700
Data Index: 5837919 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.3711. Min Act: -0.1700
Data Index: 18282 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.3711. Min Act: -0.1700
Data Index: 4488298 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.3711. Min Act: -0.1700
Data Index: 7632477 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.3398. Min Act: -0.1700
Data Index: 7229957 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6211. Min Range: -7.6211
Max Act: 7.3086. Min Act: -0.1700
Data Index: 6474098 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19