Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.9610. Min Act: -0.1697
Data Index: 3416831 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8985. Min Act: -0.1699
Data Index: 7653282 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8673. Min Act: -0.1694
Data Index: 7167903 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8673. Min Act: -0.1698
Data Index: 36957 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8673. Min Act: -0.1699
Data Index: 1032837 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 1956508 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 7461733 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8360. Min Act: -0.1700
Data Index: 6312649 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 4348831 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1695
Data Index: 8343263 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 7737149 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1697
Data Index: 1149120 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1697
Data Index: 6247002 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 5763224 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 5627088 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1630
Data Index: 5614988 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 4629847 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 4499800 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.8048. Min Act: -0.1700
Data Index: 3641307 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9610. Min Range: -4.9610
Max Act: 4.7735. Min Act: -0.1700
Data Index: 3624249 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19