Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.9053. Min Act: -0.1700
Data Index: 8550550 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.8115. Min Act: -0.1700
Data Index: 6359700 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.8271. Min Act: -0.1700
Data Index: 7645688 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7959. Min Act: -0.1700
Data Index: 8334293 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7646. Min Act: -0.1700
Data Index: 5237674 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7646. Min Act: -0.1700
Data Index: 1991635 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7802. Min Act: -0.1700
Data Index: 796100 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7490. Min Act: -0.1700
Data Index: 2527521 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7333. Min Act: -0.1700
Data Index: 7417363 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7333. Min Act: -0.1700
Data Index: 4373709 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7333. Min Act: -0.1700
Data Index: 1810523 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7020. Min Act: -0.1700
Data Index: 5525244 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7177. Min Act: -0.1700
Data Index: 41507 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7020. Min Act: -0.1700
Data Index: 257199 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7020. Min Act: -0.1700
Data Index: 119022 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.6864. Min Act: -0.1700
Data Index: 150256 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.6864. Min Act: -0.1700
Data Index: 1656392 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7177. Min Act: -0.1700
Data Index: 1978651 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.7020. Min Act: -0.1700
Data Index: 1528564 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9053. Min Range: -3.9053
Max Act: 3.6707. Min Act: -0.1700
Data Index: 5161884 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19