Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 779 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2760. Min Range: -7.2760
Max Act: 7.2760. Min Act: -0.1700
Data Index: 5344758 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2760. Min Range: -7.2760
Max Act: 7.1510. Min Act: -0.1700
Data Index: 5584442 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2760. Min Range: -7.2760
Max Act: 7.0572. Min Act: -0.1700
Data Index: 2690377 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2760. Min Range: -7.2760
Max Act: 7.0572. Min Act: -0.1700
Data Index: 6314594 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2760. Min Range: -7.2760
Max Act: 7.0260. Min Act: -0.1700
Data Index: 2849723 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.9947. Min Act: -0.1700
Data Index: 6685255 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.9322. Min Act: -0.1700
Data Index: 2902277 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.9010. Min Act: -0.1700
Data Index: 8292997 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.8697. Min Act: -0.1700
Data Index: 2654203 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.8697. Min Act: -0.1700
Data Index: 7870925 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.8385. Min Act: -0.1700
Data Index: 575860 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.8385. Min Act: -0.1700
Data Index: 5201137 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.8072. Min Act: -0.1700
Data Index: 186710 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.8072. Min Act: -0.1700
Data Index: 8047525 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.7760. Min Act: -0.1700
Data Index: 1918659 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.7447. Min Act: -0.1700
Data Index: 358155 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.7447. Min Act: -0.1700
Data Index: 996772 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.7447. Min Act: -0.1700
Data Index: 5842863 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.7135. Min Act: -0.1700
Data Index: 4630973 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2760. Min Range: -7.2760
Max Act: 6.6822. Min Act: -0.1700
Data Index: 661113 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19