Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4448 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 4281036 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.2577. Min Act: -0.1700
Data Index: 4532951 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1327. Min Act: -0.1700
Data Index: 8439977 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1327. Min Act: -0.1700
Data Index: 6984786 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 7724680 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1327. Min Act: -0.1700
Data Index: 3821655 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 5412881 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.1015. Min Act: -0.1700
Data Index: 7585596 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 8448965 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0702. Min Act: -0.1700
Data Index: 7104175 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 1324739 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 6428822 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0390. Min Act: -0.1700
Data Index: 2077126 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3515. Min Range: -5.3515
Max Act: 5.0077. Min Act: -0.1700
Data Index: 1832220 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 1392905 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 2132060 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 5176691 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 5807710 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9765. Min Act: -0.1700
Data Index: 6738943 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3515. Min Range: -5.3515
Max Act: 4.9452. Min Act: -0.1700
Data Index: 872987 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19