Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.6049. Min Act: -0.1700
Data Index: 4022334 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.4174. Min Act: -0.1699
Data Index: 3369853 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.4174. Min Act: -0.1700
Data Index: 4527566 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3862. Min Act: -0.1700
Data Index: 7908994 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3549. Min Act: -0.1700
Data Index: 3328615 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3549. Min Act: -0.1700
Data Index: 4336 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3237. Min Act: -0.1700
Data Index: 4810211 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3549. Min Act: -0.1700
Data Index: 1891302 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3237. Min Act: -0.1700
Data Index: 1278584 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3237. Min Act: -0.1700
Data Index: 7482219 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3237. Min Act: -0.1700
Data Index: 1991600 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3237. Min Act: -0.1700
Data Index: 6315388 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.3237. Min Act: -0.1700
Data Index: 1496386 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.2924. Min Act: -0.1700
Data Index: 5084650 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.2924. Min Act: -0.1700
Data Index: 368995 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.2924. Min Act: -0.1700
Data Index: 47607 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.2924. Min Act: -0.1700
Data Index: 96391 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.2924. Min Act: -0.1700
Data Index: 6148501 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.2612. Min Act: -0.1700
Data Index: 3811804 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6049. Min Range: -6.6049
Max Act: 6.2612. Min Act: -0.1700
Data Index: 263729 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19