Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4183 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.9532. Min Act: -0.1700
Data Index: 8651520 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.8898. Min Act: -0.1700
Data Index: 4733455 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.8580. Min Act: -0.1700
Data Index: 2328020 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.8262. Min Act: -0.1700
Data Index: 4577070 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.8262. Min Act: -0.1700
Data Index: 718590 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.8103. Min Act: -0.1700
Data Index: 1639780 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.8103. Min Act: -0.1700
Data Index: 325552 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7944. Min Act: -0.1700
Data Index: 6628849 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7944. Min Act: -0.1700
Data Index: 6700350 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7785. Min Act: -0.1700
Data Index: 1337223 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7625. Min Act: -0.1700
Data Index: 8781666 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7944. Min Act: -0.1700
Data Index: 6083388 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7785. Min Act: -0.1700
Data Index: 5840307 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7625. Min Act: -0.1700
Data Index: 3160245 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7625. Min Act: -0.1700
Data Index: 3138595 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7466. Min Act: -0.1700
Data Index: 6568888 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7466. Min Act: -0.1700
Data Index: 8781730 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7625. Min Act: -0.1700
Data Index: 3734259 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7466. Min Act: -0.1700
Data Index: 3863189 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9532. Min Range: -2.9532
Max Act: 2.7306. Min Act: -0.1700
Data Index: 4156629 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19