Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5461 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.9641. Min Act: -0.1700
Data Index: 7094163 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.6516. Min Act: -0.1700
Data Index: 2931259 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.5266. Min Act: -0.1700
Data Index: 2006659 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4641. Min Act: -0.1700
Data Index: 7775398 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4641. Min Act: -0.1700
Data Index: 6267399 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4641. Min Act: -0.1700
Data Index: 7809642 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4641. Min Act: -0.1700
Data Index: 2379827 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4329. Min Act: -0.1700
Data Index: 7637088 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4329. Min Act: -0.1700
Data Index: 4935137 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4016. Min Act: -0.1700
Data Index: 5978394 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4016. Min Act: -0.1700
Data Index: 8061159 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.4016. Min Act: -0.1700
Data Index: 8707907 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.3704. Min Act: -0.1700
Data Index: 327550 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.3391. Min Act: -0.1700
Data Index: 2058034 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.3079. Min Act: -0.1700
Data Index: 317694 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.3079. Min Act: -0.1700
Data Index: 5161509 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.2766. Min Act: -0.1700
Data Index: 6825806 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.2766. Min Act: -0.1700
Data Index: 6192299 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.2766. Min Act: -0.1700
Data Index: 5826510 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9641. Min Range: -7.9641
Max Act: 7.2766. Min Act: -0.1700
Data Index: 997510 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19