Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.9567. Min Act: -0.1700
Data Index: 3540509 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.8629. Min Act: -0.1700
Data Index: 8512317 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.8629. Min Act: -0.1700
Data Index: 7100064 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.8316. Min Act: -0.1700
Data Index: 8399946 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.8160. Min Act: -0.1700
Data Index: 6346005 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.8003. Min Act: -0.1700
Data Index: 5477974 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.8003. Min Act: -0.1700
Data Index: 3874704 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7847. Min Act: -0.1700
Data Index: 269857 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.8003. Min Act: -0.1700
Data Index: 5564597 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7691. Min Act: -0.1700
Data Index: 2842947 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7691. Min Act: -0.1700
Data Index: 1183062 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7378. Min Act: -0.1700
Data Index: 2498365 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7221. Min Act: -0.1700
Data Index: 3709990 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7065. Min Act: -0.1700
Data Index: 4449225 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7065. Min Act: -0.1700
Data Index: 5552517 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.6909. Min Act: -0.1700
Data Index: 3954940 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.6909. Min Act: -0.1700
Data Index: 39814 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7065. Min Act: -0.1700
Data Index: 8084284 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7065. Min Act: -0.1700
Data Index: 930333 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9567. Min Range: -3.9567
Max Act: 3.7065. Min Act: -0.1700
Data Index: 5843005 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19