Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5223 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.8146. Min Act: -0.1700
Data Index: 1703306 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.7208. Min Act: -0.1700
Data Index: 1019205 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.6896. Min Act: -0.1700
Data Index: 6247553 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.6583. Min Act: -0.1700
Data Index: 350817 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.6583. Min Act: -0.1700
Data Index: 4374506 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.6583. Min Act: -0.1700
Data Index: 1727669 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.6583. Min Act: -0.1700
Data Index: 5626439 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.6583. Min Act: -0.1700
Data Index: 5986000 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.6271. Min Act: -0.1692
Data Index: 6138203 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5958. Min Act: -0.1700
Data Index: 6460575 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5646. Min Act: -0.1700
Data Index: 7211663 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3369505 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5958. Min Act: -0.1700
Data Index: 7065781 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5646. Min Act: -0.1700
Data Index: 3554949 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3858855 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5333. Min Act: -0.1700
Data Index: 4555607 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5333. Min Act: -0.1700
Data Index: 8627478 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5021. Min Act: -0.1700
Data Index: 5044060 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5021. Min Act: -0.1700
Data Index: 6677121 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8146. Min Range: -5.8146
Max Act: 5.5021. Min Act: -0.1700
Data Index: 5471363 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19