Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5489 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.5268. Min Act: -0.1700
Data Index: 931991 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.4331. Min Act: -0.1700
Data Index: 4333272 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.3081. Min Act: -0.1700
Data Index: 2233228 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.2768. Min Act: -0.1700
Data Index: 2408144 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.2768. Min Act: -0.1700
Data Index: 6575709 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.2143. Min Act: -0.1700
Data Index: 430713 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.1518. Min Act: -0.1700
Data Index: 3082645 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.2143. Min Act: -0.1700
Data Index: 3803066 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.1206. Min Act: -0.1700
Data Index: 6089353 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.0581. Min Act: -0.1700
Data Index: 8133740 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.0581. Min Act: -0.1700
Data Index: 427018 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.0268. Min Act: -0.1700
Data Index: 3405107 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.0268. Min Act: -0.1700
Data Index: 232089 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5268. Min Range: -7.5268
Max Act: 7.0268. Min Act: -0.1700
Data Index: 8343707 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5268. Min Range: -7.5268
Max Act: 6.9956. Min Act: -0.1700
Data Index: 6631844 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5268. Min Range: -7.5268
Max Act: 6.9956. Min Act: -0.1700
Data Index: 8527063 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5268. Min Range: -7.5268
Max Act: 6.9643. Min Act: -0.1700
Data Index: 5400871 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5268. Min Range: -7.5268
Max Act: 6.9956. Min Act: -0.1700
Data Index: 4710148 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5268. Min Range: -7.5268
Max Act: 6.9331. Min Act: -0.1700
Data Index: 2947473 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5268. Min Range: -7.5268
Max Act: 6.9331. Min Act: -0.1700
Data Index: 6010090 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19