Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.7650. Min Act: -0.1700
Data Index: 5479569 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.7304. Min Act: -0.1700
Data Index: 2709599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.7477. Min Act: -0.1700
Data Index: 3168099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.7131. Min Act: -0.1700
Data Index: 405076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.7131. Min Act: -0.1700
Data Index: 8099567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6958. Min Act: -0.1700
Data Index: 3613818 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.7131. Min Act: -0.1700
Data Index: 3709541 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.7131. Min Act: -0.1700
Data Index: 5754026 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6958. Min Act: -0.1700
Data Index: 8539907 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6958. Min Act: -0.1700
Data Index: 6501804 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6958. Min Act: -0.1700
Data Index: 6298016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6784. Min Act: -0.1700
Data Index: 2165412 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6784. Min Act: -0.1700
Data Index: 6727275 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6784. Min Act: -0.1700
Data Index: 5997894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6784. Min Act: -0.1700
Data Index: 4703611 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6784. Min Act: -0.1700
Data Index: 3442201 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6784. Min Act: -0.1700
Data Index: 2623060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6784. Min Act: -0.1700
Data Index: 1665194 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6610. Min Act: -0.1700
Data Index: 125275 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7650. Min Range: -1.7650
Max Act: 1.6436. Min Act: -0.1700
Data Index: 1458371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19