Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6791622 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.6830. Min Act: -0.1700
Data Index: 3574919 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.6518. Min Act: -0.1700
Data Index: 3980710 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.6205. Min Act: -0.1700
Data Index: 5768909 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.5580. Min Act: -0.1700
Data Index: 8247338 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.5580. Min Act: -0.1700
Data Index: 914427 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.5580. Min Act: -0.1700
Data Index: 1253457 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.5268. Min Act: -0.1700
Data Index: 2736951 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4955. Min Act: -0.1700
Data Index: 6139715 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4955. Min Act: -0.1700
Data Index: 7124679 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.5268. Min Act: -0.1700
Data Index: 6181879 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4955. Min Act: -0.1700
Data Index: 666928 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4643. Min Act: -0.1700
Data Index: 4829197 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4643. Min Act: -0.1700
Data Index: 5449758 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4018. Min Act: -0.1700
Data Index: 3286670 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4643. Min Act: -0.1700
Data Index: 3601056 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4330. Min Act: -0.1700
Data Index: 3065884 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4018. Min Act: -0.1700
Data Index: 656768 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4018. Min Act: -0.1700
Data Index: 227299 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8081. Min Range: -4.8081
Max Act: 4.4018. Min Act: -0.1700
Data Index: 2089430 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19