Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.2803. Min Act: -0.1700
Data Index: 2238871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.2178. Min Act: -0.1700
Data Index: 4048375 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1865. Min Act: -0.1700
Data Index: 8108565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1865. Min Act: -0.1700
Data Index: 2103090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1865. Min Act: -0.1700
Data Index: 2792109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1552. Min Act: -0.1700
Data Index: 6720757 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1240. Min Act: -0.1700
Data Index: 7881423 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1240. Min Act: -0.1699
Data Index: 5249173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1240. Min Act: -0.1698
Data Index: 2088883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.1240. Min Act: -0.1700
Data Index: 3990038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 6544280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 270962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 2919503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 6599821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 3372090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 5835424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 8214311 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 8292068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 8670050 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2803. Min Range: -4.2803
Max Act: 4.0927. Min Act: -0.1700
Data Index: 4949 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19