Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.6781. Min Act: -0.1700
Data Index: 972868 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.5218. Min Act: -0.1700
Data Index: 5006394 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.5218. Min Act: -0.1700
Data Index: 6321408 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.5218. Min Act: -0.1700
Data Index: 3744622 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.5218. Min Act: -0.1700
Data Index: 760892 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.4906. Min Act: -0.1700
Data Index: 1440978 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.4593. Min Act: -0.1700
Data Index: 471945 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.4281. Min Act: -0.1700
Data Index: 1716863 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.4281. Min Act: -0.1700
Data Index: 1135912 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3968. Min Act: -0.1700
Data Index: 8632151 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3968. Min Act: -0.1700
Data Index: 3522566 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3656. Min Act: -0.1700
Data Index: 890075 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3343. Min Act: -0.1700
Data Index: 4960960 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3656. Min Act: -0.1700
Data Index: 7463702 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3343. Min Act: -0.1700
Data Index: 8582632 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3343. Min Act: -0.1700
Data Index: 1115538 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3343. Min Act: -0.1700
Data Index: 1794554 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3343. Min Act: -0.1700
Data Index: 3679088 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3343. Min Act: -0.1700
Data Index: 5618156 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6781. Min Range: -4.6781
Max Act: 4.3031. Min Act: -0.1700
Data Index: 3536648 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19