Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2462 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1160. Min Range: -5.1160
Max Act: 5.1160. Min Act: -0.1700
Data Index: 5353291 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1160. Min Range: -5.1160
Max Act: 5.1160. Min Act: -0.1700
Data Index: 6792974 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1160. Min Range: -5.1160
Max Act: 5.0847. Min Act: -0.1699
Data Index: 7878046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1160. Min Range: -5.1160
Max Act: 5.0535. Min Act: -0.1700
Data Index: 5103895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1160. Min Range: -5.1160
Max Act: 5.0535. Min Act: -0.1700
Data Index: 7752038 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1160. Min Range: -5.1160
Max Act: 5.0222. Min Act: -0.1700
Data Index: 2012329 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.9910. Min Act: -0.1700
Data Index: 6173195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.9910. Min Act: -0.1700
Data Index: 5987995 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.9597. Min Act: -0.1700
Data Index: 6771205 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.9285. Min Act: -0.1700
Data Index: 1476776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.9285. Min Act: -0.1700
Data Index: 7800420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8660. Min Act: -0.1700
Data Index: 3155369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8972. Min Act: -0.1700
Data Index: 7095215 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8660. Min Act: -0.1700
Data Index: 554990 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8972. Min Act: -0.1700
Data Index: 442049 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8972. Min Act: -0.1700
Data Index: 999411 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8972. Min Act: -0.1700
Data Index: 64610 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8972. Min Act: -0.1700
Data Index: 5804745 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8347. Min Act: -0.1700
Data Index: 2058651 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1160. Min Range: -5.1160
Max Act: 4.8660. Min Act: -0.1700
Data Index: 7211735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19