Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0544. Min Range: -4.0544
Max Act: 4.0544. Min Act: -0.1700
Data Index: 8252434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.9919. Min Act: -0.1700
Data Index: 6873707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.9919. Min Act: -0.1700
Data Index: 359084 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.9606. Min Act: -0.1700
Data Index: 6483132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.9606. Min Act: -0.1700
Data Index: 1815271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.9294. Min Act: -0.1700
Data Index: 93734 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8981. Min Act: -0.1700
Data Index: 7533803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8981. Min Act: -0.1700
Data Index: 8151919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8981. Min Act: -0.1700
Data Index: 2468994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8981. Min Act: -0.1700
Data Index: 5686936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8981. Min Act: -0.1700
Data Index: 3138191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8981. Min Act: -0.1700
Data Index: 6271851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 6118249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 2762349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 91975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 7006874 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 6005251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 2127289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 5775609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0544. Min Range: -4.0544
Max Act: 3.8668. Min Act: -0.1700
Data Index: 7271445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19