Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2635. Min Range: -6.2635
Max Act: 6.2635. Min Act: -0.1700
Data Index: 708776 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2635. Min Range: -6.2635
Max Act: 6.1698. Min Act: -0.1700
Data Index: 2188979 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.7323. Min Act: -0.1700
Data Index: 1198864 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.6385. Min Act: -0.1700
Data Index: 2709755 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.6385. Min Act: -0.1700
Data Index: 2462850 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.3885. Min Act: -0.1700
Data Index: 1739823 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.3885. Min Act: -0.1700
Data Index: 1082854 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.3260. Min Act: -0.1700
Data Index: 4883742 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.3260. Min Act: -0.1700
Data Index: 3761703 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2948. Min Act: -0.1700
Data Index: 1567364 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2948. Min Act: -0.1700
Data Index: 2640935 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2948. Min Act: -0.1700
Data Index: 4166624 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2948. Min Act: -0.1700
Data Index: 3079327 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2635. Min Act: -0.1700
Data Index: 5138781 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2635. Min Act: -0.1700
Data Index: 6864104 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2010. Min Act: -0.1700
Data Index: 3073904 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.1698. Min Act: -0.1700
Data Index: 88453 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.2323. Min Act: -0.1700
Data Index: 6773809 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.1698. Min Act: -0.1700
Data Index: 1672353 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2635. Min Range: -6.2635
Max Act: 5.1073. Min Act: -0.1700
Data Index: 3872789 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19