Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4238. Min Range: -6.4238
Max Act: 6.4238. Min Act: -0.1700
Data Index: 2664980 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4238. Min Range: -6.4238
Max Act: 6.1738. Min Act: -0.1700
Data Index: 7578016 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4238. Min Range: -6.4238
Max Act: 6.0800. Min Act: -0.1700
Data Index: 8735910 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4238. Min Range: -6.4238
Max Act: 6.0800. Min Act: -0.1700
Data Index: 7804504 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9863. Min Act: -0.1700
Data Index: 1705032 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9550. Min Act: -0.1700
Data Index: 1956180 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9550. Min Act: -0.1700
Data Index: 1193678 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9550. Min Act: -0.1700
Data Index: 4815074 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9238. Min Act: -0.1700
Data Index: 5661173 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9550. Min Act: -0.1700
Data Index: 7323699 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9238. Min Act: -0.1700
Data Index: 265647 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.9238. Min Act: -0.1700
Data Index: 8381728 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.8925. Min Act: -0.1700
Data Index: 7751107 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.8613. Min Act: -0.1700
Data Index: 2100333 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.8300. Min Act: -0.1700
Data Index: 3114762 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.8300. Min Act: -0.1700
Data Index: 3195421 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.8613. Min Act: -0.1700
Data Index: 2526457 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.8300. Min Act: -0.1700
Data Index: 7111250 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.8300. Min Act: -0.1700
Data Index: 4534799 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4238. Min Range: -6.4238
Max Act: 5.7988. Min Act: -0.1700
Data Index: 1847530 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19