Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1341 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.4418. Min Act: -0.1700
Data Index: 5557003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.4418. Min Act: -0.1700
Data Index: 4698119 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3793. Min Act: -0.1700
Data Index: 2235991 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3793. Min Act: -0.1700
Data Index: 8202893 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3793. Min Act: -0.1700
Data Index: 2620787 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3168. Min Act: -0.1700
Data Index: 5330047 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3168. Min Act: -0.1700
Data Index: 6773519 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3168. Min Act: -0.1700
Data Index: 2260421 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3168. Min Act: -0.1700
Data Index: 7856331 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2856. Min Act: -0.1700
Data Index: 1633491 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.3168. Min Act: -0.1700
Data Index: 4754938 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2856. Min Act: -0.1700
Data Index: 2577141 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2543. Min Act: -0.1700
Data Index: 1743771 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2543. Min Act: -0.1700
Data Index: 4107990 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2543. Min Act: -0.1700
Data Index: 995334 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2543. Min Act: -0.1700
Data Index: 2198887 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2543. Min Act: -0.1700
Data Index: 3626141 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2543. Min Act: -0.1700
Data Index: 7144926 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2231. Min Act: -0.1700
Data Index: 7388184 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4418. Min Range: -4.4418
Max Act: 4.2231. Min Act: -0.1700
Data Index: 4461928 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19