Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2469 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2091. Min Range: -6.2091
Max Act: 6.2091. Min Act: -0.1700
Data Index: 8610788 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2091. Min Range: -6.2091
Max Act: 6.1779. Min Act: -0.1700
Data Index: 4851762 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2091. Min Range: -6.2091
Max Act: 6.1466. Min Act: -0.1700
Data Index: 1906876 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2091. Min Range: -6.2091
Max Act: 6.0529. Min Act: -0.1700
Data Index: 1089086 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.9904. Min Act: -0.1700
Data Index: 5982534 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.9591. Min Act: -0.1700
Data Index: 8078478 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.9279. Min Act: -0.1700
Data Index: 6724237 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.9279. Min Act: -0.1700
Data Index: 1364140 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.9279. Min Act: -0.1700
Data Index: 4769157 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8966. Min Act: -0.1700
Data Index: 2271702 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8966. Min Act: -0.1700
Data Index: 1694941 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8966. Min Act: -0.1700
Data Index: 4813484 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8966. Min Act: -0.1700
Data Index: 5445637 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8654. Min Act: -0.1700
Data Index: 4608927 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8654. Min Act: -0.1700
Data Index: 7804357 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8341. Min Act: -0.1700
Data Index: 7915726 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8029. Min Act: -0.1700
Data Index: 2015649 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8341. Min Act: -0.1700
Data Index: 7672862 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8029. Min Act: -0.1700
Data Index: 3474382 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2091. Min Range: -6.2091
Max Act: 5.8341. Min Act: -0.1700
Data Index: 2576714 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19