Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.7758. Min Act: -0.1700
Data Index: 7759320 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.7133. Min Act: -0.1700
Data Index: 7378727 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.7446. Min Act: -0.1700
Data Index: 3622150 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.7133. Min Act: -0.1700
Data Index: 3210650 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.6821. Min Act: -0.1700
Data Index: 3987210 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.6508. Min Act: -0.1700
Data Index: 3672531 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.6196. Min Act: -0.1700
Data Index: 2088037 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.6196. Min Act: -0.1700
Data Index: 1510136 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.6196. Min Act: -0.1700
Data Index: 8229981 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.6196. Min Act: -0.1700
Data Index: 8229995 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5883. Min Act: -0.1699
Data Index: 7393956 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 3641263 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5883. Min Act: -0.1700
Data Index: 1510147 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 5150172 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 2696772 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 7422446 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 707147 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 5611665 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 1074022 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7758. Min Range: -5.7758
Max Act: 5.5571. Min Act: -0.1700
Data Index: 7339320 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19