Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.5815. Min Act: -0.1695
Data Index: 3549016 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1700
Data Index: 7015840 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.5190. Min Act: -0.1700
Data Index: 2372349 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1687
Data Index: 1018442 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1698
Data Index: 4480534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1700
Data Index: 3269726 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1699
Data Index: 6724329 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1700
Data Index: 5906867 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1700
Data Index: 5670244 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1699
Data Index: 2794168 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1696
Data Index: 2347383 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1690
Data Index: 5045574 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1700
Data Index: 1920792 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.4565. Min Act: -0.1700
Data Index: 3578823 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.3940. Min Act: -0.1699
Data Index: 315028 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.3940. Min Act: -0.1700
Data Index: 175305 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.3940. Min Act: -0.1700
Data Index: 3438928 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.3940. Min Act: -0.1699
Data Index: 291943 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.3940. Min Act: -0.1700
Data Index: 987886 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.3940. Min Act: -0.1699
Data Index: 1382981 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19