Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.9755. Min Act: -0.1700
Data Index: 6584805 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.9443. Min Act: -0.1700
Data Index: 8411197 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.9443. Min Act: -0.1700
Data Index: 755891 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.8818. Min Act: -0.1700
Data Index: 8824392 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.8193. Min Act: -0.1700
Data Index: 755892 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7568. Min Act: -0.1700
Data Index: 7191529 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7568. Min Act: -0.1700
Data Index: 6561750 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7255. Min Act: -0.1700
Data Index: 3683290 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7568. Min Act: -0.1700
Data Index: 6335180 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7568. Min Act: -0.1700
Data Index: 287661 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7568. Min Act: -0.1700
Data Index: 183106 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7255. Min Act: -0.1700
Data Index: 6249094 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7255. Min Act: -0.1700
Data Index: 4496781 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7255. Min Act: -0.1700
Data Index: 6351392 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.7255. Min Act: -0.1700
Data Index: 2167568 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.6943. Min Act: -0.1700
Data Index: 7122750 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.6943. Min Act: -0.1700
Data Index: 7191518 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.6630. Min Act: -0.1700
Data Index: 4770648 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.6943. Min Act: -0.1700
Data Index: 4742653 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9755. Min Range: -4.9755
Max Act: 4.6943. Min Act: -0.1700
Data Index: 4261037 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19