Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5356 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1858. Min Range: -5.1858
Max Act: 5.1858. Min Act: -0.1700
Data Index: 6524925 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1858. Min Range: -5.1858
Max Act: 5.1233. Min Act: -0.1700
Data Index: 8257595 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1858. Min Range: -5.1858
Max Act: 5.0921. Min Act: -0.1700
Data Index: 6303529 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1858. Min Range: -5.1858
Max Act: 5.0296. Min Act: -0.1700
Data Index: 3642344 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1858. Min Range: -5.1858
Max Act: 5.0296. Min Act: -0.1700
Data Index: 3216777 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1858. Min Range: -5.1858
Max Act: 5.0608. Min Act: -0.1700
Data Index: 7954529 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9983. Min Act: -0.1700
Data Index: 1865913 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9671. Min Act: -0.1700
Data Index: 4761069 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9671. Min Act: -0.1700
Data Index: 1679185 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9671. Min Act: -0.1700
Data Index: 2757020 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9671. Min Act: -0.1700
Data Index: 1682932 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9671. Min Act: -0.1700
Data Index: 2048836 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9358. Min Act: -0.1700
Data Index: 1344240 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9358. Min Act: -0.1700
Data Index: 6027336 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9046. Min Act: -0.1700
Data Index: 4957065 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.9046. Min Act: -0.1700
Data Index: 1697240 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.8733. Min Act: -0.1700
Data Index: 4150471 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.8733. Min Act: -0.1700
Data Index: 564145 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.8733. Min Act: -0.1700
Data Index: 1234207 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1858. Min Range: -5.1858
Max Act: 4.8733. Min Act: -0.1700
Data Index: 1926746 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19