Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.4663. Min Act: -0.1700
Data Index: 4540347 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.3101. Min Act: -0.1700
Data Index: 3720136 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.2788. Min Act: -0.1700
Data Index: 494421 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.2788. Min Act: -0.1700
Data Index: 4627775 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1850. Min Act: -0.1700
Data Index: 4989313 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1225. Min Act: -0.1700
Data Index: 714871 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.0913. Min Act: -0.1700
Data Index: 6514981 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.0288. Min Act: -0.1700
Data Index: 8247513 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9975. Min Act: -0.1700
Data Index: 7898837 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9975. Min Act: -0.1700
Data Index: 3444461 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9350. Min Act: -0.1700
Data Index: 5900751 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9662. Min Act: -0.1700
Data Index: 2901288 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9662. Min Act: -0.1700
Data Index: 2500257 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9662. Min Act: -0.1700
Data Index: 3931003 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9350. Min Act: -0.1700
Data Index: 2387740 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9350. Min Act: -0.1700
Data Index: 6286224 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9037. Min Act: -0.1700
Data Index: 5942790 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9037. Min Act: -0.1700
Data Index: 7028139 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9350. Min Act: -0.1700
Data Index: 6098401 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4663. Min Range: -4.4663
Max Act: 3.9350. Min Act: -0.1700
Data Index: 4493978 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19