Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.7181. Min Act: -0.1700
Data Index: 8209388 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.6244. Min Act: -0.1700
Data Index: 5893605 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.6244. Min Act: -0.1700
Data Index: 6308448 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4681. Min Act: -0.1700
Data Index: 3320792 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4369. Min Act: -0.1700
Data Index: 953793 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4369. Min Act: -0.1700
Data Index: 5913471 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4056. Min Act: -0.1700
Data Index: 7640925 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4056. Min Act: -0.1700
Data Index: 3142149 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.4056. Min Act: -0.1700
Data Index: 5106688 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3119. Min Act: -0.1700
Data Index: 4569346 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3119. Min Act: -0.1700
Data Index: 1844892 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.3119. Min Act: -0.1700
Data Index: 3327297 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2806. Min Act: -0.1700
Data Index: 3514967 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2806. Min Act: -0.1700
Data Index: 7578687 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2494. Min Act: -0.1700
Data Index: 32229 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2494. Min Act: -0.1700
Data Index: 2992729 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2494. Min Act: -0.1700
Data Index: 44087 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2494. Min Act: -0.1700
Data Index: 4742459 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2181. Min Act: -0.1700
Data Index: 4934992 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7181. Min Range: -5.7181
Max Act: 5.2181. Min Act: -0.1700
Data Index: 6549907 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19