Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.7835. Min Act: -0.1700
Data Index: 6278983 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.7835. Min Act: -0.1700
Data Index: 6049230 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.5648. Min Act: -0.1700
Data Index: 7422696 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.5335. Min Act: -0.1700
Data Index: 2819824 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.4710. Min Act: -0.1700
Data Index: 123781 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.5023. Min Act: -0.1700
Data Index: 5667524 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.5023. Min Act: -0.1700
Data Index: 6243633 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.4398. Min Act: -0.1700
Data Index: 1254506 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.3773. Min Act: -0.1700
Data Index: 3223128 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.3773. Min Act: -0.1700
Data Index: 8554898 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.3148. Min Act: -0.1700
Data Index: 4868254 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2835. Min Act: -0.1700
Data Index: 8755206 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2835. Min Act: -0.1700
Data Index: 4676517 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2835. Min Act: -0.1700
Data Index: 8558986 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2523. Min Act: -0.1700
Data Index: 7418854 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2523. Min Act: -0.1700
Data Index: 2485986 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2835. Min Act: -0.1700
Data Index: 1335185 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2523. Min Act: -0.1700
Data Index: 7692276 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2210. Min Act: -0.1700
Data Index: 7200320 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7835. Min Range: -7.7835
Max Act: 7.2210. Min Act: -0.1700
Data Index: 3504917 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19