Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 304 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.7801. Min Act: -0.1700
Data Index: 4619717 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.7176. Min Act: -0.1700
Data Index: 5557930 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.6238. Min Act: -0.1700
Data Index: 7215146 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.6551. Min Act: -0.1700
Data Index: 7800446 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.5926. Min Act: -0.1700
Data Index: 4777172 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.5926. Min Act: -0.1700
Data Index: 8815235 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.5613. Min Act: -0.1700
Data Index: 4739531 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4988. Min Act: -0.1700
Data Index: 8807293 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.5301. Min Act: -0.1700
Data Index: 5253344 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4988. Min Act: -0.1700
Data Index: 2997860 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4676. Min Act: -0.1700
Data Index: 2775649 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4676. Min Act: -0.1700
Data Index: 1062028 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4363. Min Act: -0.1700
Data Index: 1844309 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 885705 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.4051. Min Act: -0.1700
Data Index: 3215301 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3738. Min Act: -0.1700
Data Index: 8196601 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3426. Min Act: -0.1700
Data Index: 4004874 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3738. Min Act: -0.1700
Data Index: 1438080 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3738. Min Act: -0.1700
Data Index: 5977040 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7801. Min Range: -5.7801
Max Act: 5.3738. Min Act: -0.1700
Data Index: 4064590 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19