Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.7462. Min Act: -0.1700
Data Index: 8169176 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.7149. Min Act: -0.1700
Data Index: 2888287 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.6837. Min Act: -0.1700
Data Index: 6927313 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.6212. Min Act: -0.1700
Data Index: 5000858 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.6212. Min Act: -0.1700
Data Index: 18083 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.6212. Min Act: -0.1700
Data Index: 8814723 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.6212. Min Act: -0.1700
Data Index: 8438971 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5899. Min Act: -0.1700
Data Index: 3573919 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5274. Min Act: -0.1700
Data Index: 2605207 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5274. Min Act: -0.1700
Data Index: 3767160 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.5274. Min Act: -0.1700
Data Index: 4373375 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4962. Min Act: -0.1700
Data Index: 7602173 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 8486841 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 2438016 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 3559025 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 201497 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6890627 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 5892480 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3319569 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7462. Min Range: -4.7462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 1299304 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19