Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1635. Min Range: -7.1635
Max Act: 7.1635. Min Act: -0.1700
Data Index: 6328828 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.9760. Min Act: -0.1700
Data Index: 5865247 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.9135. Min Act: -0.1700
Data Index: 4743145 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.7885. Min Act: -0.1700
Data Index: 7311909 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.7572. Min Act: -0.1700
Data Index: 3014788 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.7260. Min Act: -0.1700
Data Index: 8668967 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.6322. Min Act: -0.1700
Data Index: 859567 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.5697. Min Act: -0.1700
Data Index: 8000366 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.5385. Min Act: -0.1700
Data Index: 4510831 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.5385. Min Act: -0.1700
Data Index: 900603 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.4760. Min Act: -0.1700
Data Index: 3360645 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.4760. Min Act: -0.1700
Data Index: 713022 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.4760. Min Act: -0.1700
Data Index: 5598947 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.4447. Min Act: -0.1700
Data Index: 799746 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.4447. Min Act: -0.1700
Data Index: 971318 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.4135. Min Act: -0.1700
Data Index: 4904300 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.4135. Min Act: -0.1700
Data Index: 4241590 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.3822. Min Act: -0.1700
Data Index: 6828463 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.3822. Min Act: -0.1700
Data Index: 1053344 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1635. Min Range: -7.1635
Max Act: 6.3510. Min Act: -0.1700
Data Index: 515261 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19