Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.6272. Min Act: -0.1700
Data Index: 6692523 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.5022. Min Act: -0.1700
Data Index: 2947870 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.4397. Min Act: -0.1700
Data Index: 6794062 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.2209. Min Act: -0.1700
Data Index: 5837289 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1897. Min Act: -0.1700
Data Index: 389192 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1897. Min Act: -0.1700
Data Index: 1661229 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1584. Min Act: -0.1700
Data Index: 7290376 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1584. Min Act: -0.1700
Data Index: 3821238 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1584. Min Act: -0.1700
Data Index: 4163694 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1272. Min Act: -0.1700
Data Index: 6404989 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1272. Min Act: -0.1700
Data Index: 6817887 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1272. Min Act: -0.1700
Data Index: 1025520 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.1272. Min Act: -0.1700
Data Index: 1332610 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.0959. Min Act: -0.1700
Data Index: 839545 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.0959. Min Act: -0.1700
Data Index: 8393784 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.0647. Min Act: -0.1700
Data Index: 7189721 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.0334. Min Act: -0.1700
Data Index: 694713 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.0334. Min Act: -0.1700
Data Index: 6731946 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.0334. Min Act: -0.1700
Data Index: 786536 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6272. Min Range: -5.6272
Max Act: 5.0334. Min Act: -0.1700
Data Index: 3610101 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19