Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4473 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3391. Min Range: -7.3391
Max Act: 7.3391. Min Act: -0.1700
Data Index: 5088514 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.8078. Min Act: -0.1700
Data Index: 293449 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.7141. Min Act: -0.1700
Data Index: 3657319 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.6516. Min Act: -0.1700
Data Index: 4562207 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.4953. Min Act: -0.1700
Data Index: 4582915 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.4953. Min Act: -0.1700
Data Index: 838714 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.4641. Min Act: -0.1700
Data Index: 223400 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.4328. Min Act: -0.1700
Data Index: 2697242 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.4016. Min Act: -0.1700
Data Index: 125393 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.3391. Min Act: -0.1700
Data Index: 5507853 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.3078. Min Act: -0.1700
Data Index: 5804496 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.2766. Min Act: -0.1700
Data Index: 4069820 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.2453. Min Act: -0.1700
Data Index: 4967482 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.2453. Min Act: -0.1700
Data Index: 6740318 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.2766. Min Act: -0.1700
Data Index: 745392 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.2141. Min Act: -0.1700
Data Index: 5457290 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.1828. Min Act: -0.1700
Data Index: 8442179 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.2141. Min Act: -0.1700
Data Index: 7456596 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.1828. Min Act: -0.1700
Data Index: 7160946 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3391. Min Range: -7.3391
Max Act: 6.1828. Min Act: -0.1700
Data Index: 3273972 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19