Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0482. Min Range: -10.0482
Max Act: 10.0482. Min Act: -0.1700
Data Index: 5396570 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.8607. Min Act: -0.1700
Data Index: 6444293 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.7982. Min Act: -0.1700
Data Index: 4110603 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.6107. Min Act: -0.1700
Data Index: 3880581 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.6107. Min Act: -0.1700
Data Index: 7131244 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.5482. Min Act: -0.1700
Data Index: 8061677 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.5482. Min Act: -0.1700
Data Index: 5141396 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.4857. Min Act: -0.1700
Data Index: 3683215 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.4857. Min Act: -0.1700
Data Index: 2701339 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 2757857 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 1987020 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 8029919 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 5614074 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 7462163 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 4578711 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 1675356 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 2002462 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 479160 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.3607. Min Act: -0.1700
Data Index: 5167723 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0482. Min Range: -10.0482
Max Act: 9.2982. Min Act: -0.1700
Data Index: 4236072 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19