Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 545 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1231. Min Range: -4.1231
Max Act: 4.1231. Min Act: -0.1700
Data Index: 8287641 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9981. Min Act: -0.1700
Data Index: 4135112 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9356. Min Act: -0.1700
Data Index: 5217184 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9043. Min Act: -0.1700
Data Index: 2220321 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9043. Min Act: -0.1700
Data Index: 959242 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8418. Min Act: -0.1700
Data Index: 3787221 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8730. Min Act: -0.1700
Data Index: 4075094 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8730. Min Act: -0.1700
Data Index: 6084938 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8418. Min Act: -0.1700
Data Index: 2210369 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8418. Min Act: -0.1700
Data Index: 8395140 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8418. Min Act: -0.1700
Data Index: 3428931 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.7792. Min Act: -0.1700
Data Index: 6075607 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 8167605 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 2415380 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 7552763 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 1013973 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.7792. Min Act: -0.1700
Data Index: 5964854 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.7792. Min Act: -0.1700
Data Index: 1956154 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.7479. Min Act: -0.1700
Data Index: 4275788 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.7479. Min Act: -0.1700
Data Index: 4942021 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19