Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.3238. Min Act: -0.1700
Data Index: 3773161 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.2926. Min Act: -0.1700
Data Index: 5555124 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.2926. Min Act: -0.1700
Data Index: 7241867 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.2301. Min Act: -0.1700
Data Index: 3307563 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.2613. Min Act: -0.1700
Data Index: 4087048 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.2301. Min Act: -0.1700
Data Index: 8728264 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.2301. Min Act: -0.1700
Data Index: 3627210 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1988. Min Act: -0.1700
Data Index: 5326549 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1676. Min Act: -0.1700
Data Index: 2903760 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1676. Min Act: -0.1700
Data Index: 5824234 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1676. Min Act: -0.1700
Data Index: 3150506 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1363. Min Act: -0.1700
Data Index: 6328118 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1363. Min Act: -0.1700
Data Index: 3041230 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1051. Min Act: -0.1700
Data Index: 2137016 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.1051. Min Act: -0.1700
Data Index: 4799548 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.0426. Min Act: -0.1700
Data Index: 2405148 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.0738. Min Act: -0.1700
Data Index: 5107940 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.0738. Min Act: -0.1700
Data Index: 7134086 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.0738. Min Act: -0.1700
Data Index: 4857152 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3238. Min Range: -5.3238
Max Act: 5.0738. Min Act: -0.1700
Data Index: 1409233 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19