Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 800 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.2806. Min Act: -0.1700
Data Index: 2138845 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.2806. Min Act: -0.1700
Data Index: 3767400 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.2335. Min Act: -0.1700
Data Index: 6994445 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.2020. Min Act: -0.1700
Data Index: 3734586 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.1863. Min Act: -0.1700
Data Index: 7544377 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.1706. Min Act: -0.1700
Data Index: 6461354 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.1391. Min Act: -0.1700
Data Index: 5592792 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.1233. Min Act: -0.1700
Data Index: 5111240 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.1233. Min Act: -0.1700
Data Index: 6994444 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.1076. Min Act: -0.1700
Data Index: 4120731 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.1076. Min Act: -0.1700
Data Index: 3030140 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0918. Min Act: -0.1700
Data Index: 7182321 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0761. Min Act: -0.1700
Data Index: 8721999 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0603. Min Act: -0.1700
Data Index: 6461355 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0287. Min Act: -0.1700
Data Index: 8774967 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0761. Min Act: -0.1700
Data Index: 7749327 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0287. Min Act: -0.1700
Data Index: 1081555 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0129. Min Act: -0.1700
Data Index: 386194 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0129. Min Act: -0.1700
Data Index: 226542 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2806. Min Range: -3.2806
Max Act: 3.0287. Min Act: -0.1700
Data Index: 4953054 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19