Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4847 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.2148. Min Act: -0.1694
Data Index: 8780866 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.2148. Min Act: -0.1696
Data Index: 2907486 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1836. Min Act: -0.1694
Data Index: 7500844 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1836. Min Act: -0.1694
Data Index: 2059852 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1523. Min Act: -0.1700
Data Index: 8426964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1694
Data Index: 6268399 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1699
Data Index: 8027249 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1694
Data Index: 2646703 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1697
Data Index: 7127719 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1700
Data Index: 1783437 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1700
Data Index: 1454577 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1694
Data Index: 8146455 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1700
Data Index: 8252707 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1699
Data Index: 7195160 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1694
Data Index: 7484036 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1696
Data Index: 2849890 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1699
Data Index: 6135848 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1695
Data Index: 2085487 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1698
Data Index: 86187 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2148. Min Range: -5.2148
Max Act: 5.1211. Min Act: -0.1694
Data Index: 5607924 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19