Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2693 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.2246. Min Act: -0.1700
Data Index: 5872120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.2246. Min Act: -0.1700
Data Index: 5216981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.2246. Min Act: -0.1700
Data Index: 3909548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1934. Min Act: -0.1700
Data Index: 8481606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1934. Min Act: -0.1700
Data Index: 3829558 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1621. Min Act: -0.1699
Data Index: 5827866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1621. Min Act: -0.1700
Data Index: 6756495 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1621. Min Act: -0.1700
Data Index: 8198692 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1621. Min Act: -0.1700
Data Index: 2247023 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1621. Min Act: -0.1700
Data Index: 250253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1309. Min Act: -0.1700
Data Index: 6563717 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1309. Min Act: -0.1700
Data Index: 7687568 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1621. Min Act: -0.1700
Data Index: 5366999 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1309. Min Act: -0.1700
Data Index: 8703503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1309. Min Act: -0.1700
Data Index: 4016155 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1309. Min Act: -0.1700
Data Index: 293079 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.0996. Min Act: -0.1700
Data Index: 34057 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.1309. Min Act: -0.1700
Data Index: 4016154 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.0996. Min Act: -0.1700
Data Index: 4230770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2246. Min Range: -5.2246
Max Act: 5.0996. Min Act: -0.1700
Data Index: 4292120 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19