Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3251. Min Range: -8.3251
Max Act: 8.3251. Min Act: -0.1700
Data Index: 5803868 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3251. Min Range: -8.3251
Max Act: 8.0126. Min Act: -0.1700
Data Index: 3626908 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.9501. Min Act: -0.1700
Data Index: 6236481 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.8251. Min Act: -0.1700
Data Index: 3685213 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.8251. Min Act: -0.1700
Data Index: 5850771 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.7626. Min Act: -0.1700
Data Index: 4681324 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.7001. Min Act: -0.1700
Data Index: 6379090 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.6689. Min Act: -0.1700
Data Index: 8554140 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.6689. Min Act: -0.1700
Data Index: 3133416 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.6689. Min Act: -0.1700
Data Index: 6102433 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.6689. Min Act: -0.1700
Data Index: 4508725 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.6376. Min Act: -0.1700
Data Index: 3638524 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.6376. Min Act: -0.1700
Data Index: 6260223 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.6064. Min Act: -0.1700
Data Index: 876681 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.5751. Min Act: -0.1700
Data Index: 3873960 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.5439. Min Act: -0.1700
Data Index: 8416605 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.5126. Min Act: -0.1700
Data Index: 1116644 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.4814. Min Act: -0.1700
Data Index: 6923456 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.5126. Min Act: -0.1700
Data Index: 244133 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3251. Min Range: -8.3251
Max Act: 7.4814. Min Act: -0.1700
Data Index: 5653796 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19