Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.5290. Min Act: -0.1700
Data Index: 2578228 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.4977. Min Act: -0.1700
Data Index: 442648 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.3727. Min Act: -0.1700
Data Index: 2081230 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.3415. Min Act: -0.1700
Data Index: 1296166 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.3415. Min Act: -0.1700
Data Index: 7972926 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.3415. Min Act: -0.1700
Data Index: 4298385 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.2477. Min Act: -0.1700
Data Index: 3777931 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.2477. Min Act: -0.1700
Data Index: 7845603 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.2477. Min Act: -0.1700
Data Index: 1339911 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.2165. Min Act: -0.1700
Data Index: 6634624 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.1852. Min Act: -0.1700
Data Index: 7720763 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.1540. Min Act: -0.1700
Data Index: 2059260 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.1227. Min Act: -0.1700
Data Index: 5812133 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.1227. Min Act: -0.1700
Data Index: 3055552 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.0915. Min Act: -0.1700
Data Index: 7829947 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.0602. Min Act: -0.1700
Data Index: 168951 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.0602. Min Act: -0.1700
Data Index: 7075008 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.0290. Min Act: -0.1700
Data Index: 526262 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.0290. Min Act: -0.1700
Data Index: 4526332 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5290. Min Range: -7.5290
Max Act: 7.0290. Min Act: -0.1700
Data Index: 3850266 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19