Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5338 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.5142. Min Act: -0.1700
Data Index: 845730 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.1079. Min Act: -0.1700
Data Index: 3603218 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.0454. Min Act: -0.1700
Data Index: 716158 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.0141. Min Act: -0.1700
Data Index: 5005189 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.0454. Min Act: -0.1700
Data Index: 4126480 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.0141. Min Act: -0.1700
Data Index: 7385622 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.0141. Min Act: -0.1700
Data Index: 4970232 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.9516. Min Act: -0.1700
Data Index: 3481172 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.9516. Min Act: -0.1700
Data Index: 385122 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.9203. Min Act: -0.1700
Data Index: 7723005 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.9516. Min Act: -0.1700
Data Index: 4536557 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8891. Min Act: -0.1700
Data Index: 1402452 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8578. Min Act: -0.1700
Data Index: 4654211 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8578. Min Act: -0.1700
Data Index: 6869907 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8422. Min Act: -0.1700
Data Index: 2841944 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8422. Min Act: -0.1700
Data Index: 7541901 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8265. Min Act: -0.1700
Data Index: 6322016 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8109. Min Act: -0.1700
Data Index: 1695771 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8109. Min Act: -0.1700
Data Index: 6769986 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5142. Min Range: -4.5142
Max Act: 3.8109. Min Act: -0.1700
Data Index: 2159901 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19