Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 836 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0504. Min Range: -5.0504
Max Act: 5.0504. Min Act: -0.1700
Data Index: 1611159 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0504. Min Range: -5.0504
Max Act: 5.0192. Min Act: -0.1700
Data Index: 4022571 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0504. Min Range: -5.0504
Max Act: 5.0192. Min Act: -0.1700
Data Index: 4300271 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 5309044 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0504. Min Range: -5.0504
Max Act: 5.0192. Min Act: -0.1700
Data Index: 8679809 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9879. Min Act: -0.1700
Data Index: 4934120 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9567. Min Act: -0.1700
Data Index: 6816980 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9567. Min Act: -0.1700
Data Index: 7346942 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9567. Min Act: -0.1700
Data Index: 4243538 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9254. Min Act: -0.1700
Data Index: 11224 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9567. Min Act: -0.1700
Data Index: 8787581 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9567. Min Act: -0.1700
Data Index: 3544994 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9254. Min Act: -0.1700
Data Index: 4449509 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9254. Min Act: -0.1700
Data Index: 8159454 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9254. Min Act: -0.1700
Data Index: 2882309 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8942. Min Act: -0.1700
Data Index: 2218136 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9254. Min Act: -0.1700
Data Index: 912517 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.9254. Min Act: -0.1700
Data Index: 3167855 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8942. Min Act: -0.1700
Data Index: 3222066 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0504. Min Range: -5.0504
Max Act: 4.8942. Min Act: -0.1700
Data Index: 3992333 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19