Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2434 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0689. Min Range: -2.0689
Max Act: 2.0521. Min Act: -0.1700
Data Index: 5073131 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0689. Min Range: -2.0689
Max Act: 2.0689. Min Act: -0.1700
Data Index: 4828441 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0689. Min Range: -2.0689
Max Act: 2.0353. Min Act: -0.1700
Data Index: 6438332 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0689. Min Range: -2.0689
Max Act: 2.0184. Min Act: -0.1700
Data Index: 4336336 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0689. Min Range: -2.0689
Max Act: 2.0015. Min Act: -0.1700
Data Index: 5601059 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0689. Min Range: -2.0689
Max Act: 2.0015. Min Act: -0.1700
Data Index: 287346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.9846. Min Act: -0.1700
Data Index: 6533512 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.9677. Min Act: -0.1700
Data Index: 7144906 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.9337. Min Act: -0.1700
Data Index: 7144903 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.9167. Min Act: -0.1700
Data Index: 174858 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8826. Min Act: -0.1700
Data Index: 2893734 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8826. Min Act: -0.1700
Data Index: 8780293 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8655. Min Act: -0.1700
Data Index: 4875012 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8484. Min Act: -0.1700
Data Index: 4463666 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8484. Min Act: -0.1700
Data Index: 8780285 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8141. Min Act: -0.1700
Data Index: 6813989 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8312. Min Act: -0.1700
Data Index: 5214250 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8312. Min Act: -0.1700
Data Index: 390639 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8141. Min Act: -0.1700
Data Index: 2239547 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0689. Min Range: -2.0689
Max Act: 1.8312. Min Act: -0.1700
Data Index: 1325144 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19