Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2168. Min Range: -4.2168
Max Act: 4.2168. Min Act: -0.1700
Data Index: 1821501 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2168. Min Range: -4.2168
Max Act: 4.0918. Min Act: -0.1700
Data Index: 2363875 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2168. Min Range: -4.2168
Max Act: 4.0292. Min Act: -0.1700
Data Index: 5262364 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.9980. Min Act: -0.1700
Data Index: 3433515 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.9355. Min Act: -0.1700
Data Index: 1740566 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.9355. Min Act: -0.1700
Data Index: 6388305 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.9355. Min Act: -0.1700
Data Index: 7921058 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.8729. Min Act: -0.1700
Data Index: 3063953 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.8729. Min Act: -0.1700
Data Index: 3237489 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.8729. Min Act: -0.1700
Data Index: 1469789 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.9042. Min Act: -0.1700
Data Index: 3740739 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.8417. Min Act: -0.1700
Data Index: 3117100 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.8417. Min Act: -0.1700
Data Index: 6626941 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.8417. Min Act: -0.1700
Data Index: 3433517 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.7947. Min Act: -0.1700
Data Index: 5332769 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.7947. Min Act: -0.1700
Data Index: 5951954 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.7791. Min Act: -0.1700
Data Index: 2522034 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.7791. Min Act: -0.1700
Data Index: 1948037 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.7791. Min Act: -0.1700
Data Index: 4822246 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2168. Min Range: -4.2168
Max Act: 3.7791. Min Act: -0.1700
Data Index: 6947228 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19