Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1944 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2212. Min Range: -6.2212
Max Act: 6.2212. Min Act: -0.1700
Data Index: 3765806 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2212. Min Range: -6.2212
Max Act: 6.1274. Min Act: -0.1700
Data Index: 6112526 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2212. Min Range: -6.2212
Max Act: 6.0337. Min Act: -0.1700
Data Index: 2331417 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2212. Min Range: -6.2212
Max Act: 6.0024. Min Act: -0.1700
Data Index: 4715431 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2212. Min Range: -6.2212
Max Act: 6.0024. Min Act: -0.1700
Data Index: 4660252 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.9399. Min Act: -0.1700
Data Index: 2082393 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.9399. Min Act: -0.1700
Data Index: 2735851 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.8774. Min Act: -0.1700
Data Index: 4562479 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.8774. Min Act: -0.1700
Data Index: 5715455 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.8462. Min Act: -0.1700
Data Index: 7092270 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.8462. Min Act: -0.1700
Data Index: 6500973 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.8149. Min Act: -0.1700
Data Index: 7959160 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.8149. Min Act: -0.1700
Data Index: 7243836 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.7837. Min Act: -0.1700
Data Index: 2994208 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.7837. Min Act: -0.1700
Data Index: 2573533 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.7837. Min Act: -0.1700
Data Index: 5547874 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.7837. Min Act: -0.1700
Data Index: 5285659 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.7524. Min Act: -0.1700
Data Index: 233627 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.7837. Min Act: -0.1700
Data Index: 1870196 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2212. Min Range: -6.2212
Max Act: 5.7837. Min Act: -0.1700
Data Index: 343188 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19