Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2196 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.7058. Min Act: -0.1700
Data Index: 3328393 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4245. Min Act: -0.1700
Data Index: 8008959 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.3933. Min Act: -0.1700
Data Index: 7783895 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.3620. Min Act: -0.1700
Data Index: 8126399 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.3308. Min Act: -0.1700
Data Index: 482762 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.3308. Min Act: -0.1700
Data Index: 1086354 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.3308. Min Act: -0.1700
Data Index: 6596556 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2995. Min Act: -0.1700
Data Index: 5652536 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 299138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 4778703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 2376815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 7926814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 412590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 7582158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 1633013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 4328207 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 5181807 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 163309 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 7253556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.2683. Min Act: -0.1700
Data Index: 4877967 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19