Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.5979. Min Act: -0.1700
Data Index: 6615302 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.4729. Min Act: -0.1700
Data Index: 5735515 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.4104. Min Act: -0.1700
Data Index: 3847421 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.3479. Min Act: -0.1700
Data Index: 8103438 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.3479. Min Act: -0.1700
Data Index: 4013189 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.3167. Min Act: -0.1700
Data Index: 13839 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.3167. Min Act: -0.1700
Data Index: 6208972 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.3479. Min Act: -0.1700
Data Index: 764572 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.2854. Min Act: -0.1700
Data Index: 7638524 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.2854. Min Act: -0.1700
Data Index: 7638525 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.2542. Min Act: -0.1700
Data Index: 897743 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.2542. Min Act: -0.1700
Data Index: 4928382 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.2542. Min Act: -0.1700
Data Index: 4593906 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.1917. Min Act: -0.1700
Data Index: 5830271 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.1917. Min Act: -0.1700
Data Index: 3988170 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.1604. Min Act: -0.1700
Data Index: 642214 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.1604. Min Act: -0.1700
Data Index: 223364 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.1604. Min Act: -0.1700
Data Index: 443455 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.1292. Min Act: -0.1700
Data Index: 2987927 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5979. Min Range: -4.5979
Max Act: 4.1604. Min Act: -0.1700
Data Index: 3162200 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19