Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.8261. Min Act: -0.1700
Data Index: 8576878 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.7949. Min Act: -0.1700
Data Index: 1202724 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.6386. Min Act: -0.1700
Data Index: 8219900 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.6386. Min Act: -0.1700
Data Index: 1202727 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.5761. Min Act: -0.1700
Data Index: 3476719 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.4824. Min Act: -0.1700
Data Index: 6297387 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.4824. Min Act: -0.1700
Data Index: 3158920 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.4511. Min Act: -0.1700
Data Index: 2639258 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.4199. Min Act: -0.1700
Data Index: 2486045 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.4511. Min Act: -0.1700
Data Index: 5108105 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.4199. Min Act: -0.1700
Data Index: 2637657 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3886. Min Act: -0.1700
Data Index: 1695551 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3573. Min Act: -0.1700
Data Index: 8405784 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3886. Min Act: -0.1700
Data Index: 3952563 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3886. Min Act: -0.1700
Data Index: 8479349 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.4199. Min Act: -0.1700
Data Index: 3063692 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3886. Min Act: -0.1700
Data Index: 5948854 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3573. Min Act: -0.1700
Data Index: 5711623 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3573. Min Act: -0.1700
Data Index: 5804769 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8261. Min Range: -4.8261
Max Act: 4.3573. Min Act: -0.1700
Data Index: 15464 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19