Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2166 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.2461. Min Act: -0.1700
Data Index: 95819 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.2148. Min Act: -0.1700
Data Index: 5567420 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.2461. Min Act: -0.1700
Data Index: 1846386 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1836. Min Act: -0.1700
Data Index: 5289287 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1836. Min Act: -0.1698
Data Index: 8623226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1836. Min Act: -0.1700
Data Index: 6810002 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1523. Min Act: -0.1700
Data Index: 3537236 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1523. Min Act: -0.1699
Data Index: 6377324 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1211. Min Act: -0.1700
Data Index: 6107705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1211. Min Act: -0.1700
Data Index: 4969460 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1211. Min Act: -0.1700
Data Index: 7782643 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1211. Min Act: -0.1700
Data Index: 3966726 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1211. Min Act: -0.1700
Data Index: 1492455 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.0898. Min Act: -0.1700
Data Index: 197231 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.0898. Min Act: -0.1699
Data Index: 3549155 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.1211. Min Act: -0.1685
Data Index: 1657095 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.0586. Min Act: -0.1699
Data Index: 2212264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.0898. Min Act: -0.1700
Data Index: 7673371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.0898. Min Act: -0.1695
Data Index: 325064 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2461. Min Range: -5.2461
Max Act: 5.0898. Min Act: -0.1699
Data Index: 78495 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19