Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.4303. Min Act: -0.1700
Data Index: 5117512 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.2740. Min Act: -0.1700
Data Index: 8074818 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.2740. Min Act: -0.1700
Data Index: 8522716 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.2115. Min Act: -0.1700
Data Index: 4522651 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.1490. Min Act: -0.1700
Data Index: 1240435 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0865. Min Act: -0.1700
Data Index: 2498544 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0865. Min Act: -0.1700
Data Index: 5941764 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0553. Min Act: -0.1700
Data Index: 3212203 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0553. Min Act: -0.1700
Data Index: 5404779 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9928. Min Act: -0.1700
Data Index: 4639117 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0240. Min Act: -0.1700
Data Index: 6302331 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9928. Min Act: -0.1700
Data Index: 6716545 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9928. Min Act: -0.1700
Data Index: 200818 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9303. Min Act: -0.1700
Data Index: 876990 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9303. Min Act: -0.1700
Data Index: 5189115 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9303. Min Act: -0.1700
Data Index: 6477438 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9303. Min Act: -0.1700
Data Index: 5764468 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.8990. Min Act: -0.1700
Data Index: 7453859 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.8678. Min Act: -0.1700
Data Index: 8001124 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.8678. Min Act: -0.1700
Data Index: 2910199 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19