Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.8829. Min Act: -0.1700
Data Index: 8271115 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.7267. Min Act: -0.1700
Data Index: 1244130 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.7267. Min Act: -0.1700
Data Index: 2241966 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.4454. Min Act: -0.1700
Data Index: 250203 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.3829. Min Act: -0.1700
Data Index: 5500026 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.3517. Min Act: -0.1700
Data Index: 5592337 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.3829. Min Act: -0.1700
Data Index: 3049841 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.3517. Min Act: -0.1700
Data Index: 5883122 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.3517. Min Act: -0.1700
Data Index: 6804177 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.2892. Min Act: -0.1700
Data Index: 6060582 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.2579. Min Act: -0.1700
Data Index: 2210546 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.2579. Min Act: -0.1700
Data Index: 2634032 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.2579. Min Act: -0.1700
Data Index: 5680204 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.2267. Min Act: -0.1700
Data Index: 1540075 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.2267. Min Act: -0.1700
Data Index: 6741877 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.1954. Min Act: -0.1700
Data Index: 3622356 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.1954. Min Act: -0.1700
Data Index: 6557375 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.1954. Min Act: -0.1700
Data Index: 7204370 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.1954. Min Act: -0.1700
Data Index: 1212950 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8829. Min Range: -6.8829
Max Act: 6.1642. Min Act: -0.1700
Data Index: 7182430 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19