Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.4962. Min Act: -0.1700
Data Index: 4496303 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.4024. Min Act: -0.1700
Data Index: 2688106 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.4024. Min Act: -0.1700
Data Index: 7509856 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.3399. Min Act: -0.1700
Data Index: 1391652 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.1524. Min Act: -0.1700
Data Index: 6634484 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.1524. Min Act: -0.1700
Data Index: 5038619 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.1524. Min Act: -0.1700
Data Index: 5309964 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.0899. Min Act: -0.1700
Data Index: 7566591 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.0587. Min Act: -0.1700
Data Index: 4784950 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.9962. Min Act: -0.1700
Data Index: 1864332 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4962. Min Range: -6.4962
Max Act: 6.0274. Min Act: -0.1700
Data Index: 3643521 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.9962. Min Act: -0.1700
Data Index: 8116384 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.9962. Min Act: -0.1700
Data Index: 2439136 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.9337. Min Act: -0.1700
Data Index: 7677892 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.9024. Min Act: -0.1700
Data Index: 5467471 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.8399. Min Act: -0.1700
Data Index: 5919181 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.8712. Min Act: -0.1700
Data Index: 2983142 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.8712. Min Act: -0.1700
Data Index: 2335538 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.8399. Min Act: -0.1700
Data Index: 5666075 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4962. Min Range: -6.4962
Max Act: 5.8399. Min Act: -0.1700
Data Index: 8656701 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19