Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.7814. Min Act: -0.1700
Data Index: 1029832 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.7814. Min Act: -0.1700
Data Index: 5202063 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.7016. Min Act: -0.1700
Data Index: 7262281 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.7016. Min Act: -0.1700
Data Index: 8212663 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.6695. Min Act: -0.1700
Data Index: 7447802 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.6375. Min Act: -0.1700
Data Index: 8332260 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.6375. Min Act: -0.1700
Data Index: 1880276 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.6053. Min Act: -0.1700
Data Index: 5656085 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.6053. Min Act: -0.1700
Data Index: 6939621 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.6053. Min Act: -0.1700
Data Index: 3727212 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5892. Min Act: -0.1700
Data Index: 5565530 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.6053. Min Act: -0.1700
Data Index: 3580345 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5731. Min Act: -0.1700
Data Index: 1895092 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5570. Min Act: -0.1700
Data Index: 7011278 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5570. Min Act: -0.1700
Data Index: 6846953 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5408. Min Act: -0.1700
Data Index: 827204 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5408. Min Act: -0.1700
Data Index: 6789150 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5247. Min Act: -0.1700
Data Index: 1637927 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5085. Min Act: -0.1700
Data Index: 7553851 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7814. Min Range: -2.7814
Max Act: 2.5085. Min Act: -0.1700
Data Index: 3446233 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19