Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5325 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.7687. Min Act: -0.1700
Data Index: 4468670 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.7374. Min Act: -0.1700
Data Index: 8005877 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.5499. Min Act: -0.1700
Data Index: 3126133 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.4562. Min Act: -0.1700
Data Index: 276785 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.3624. Min Act: -0.1700
Data Index: 2060669 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.3624. Min Act: -0.1700
Data Index: 6842280 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.3312. Min Act: -0.1700
Data Index: 5017540 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.3312. Min Act: -0.1700
Data Index: 5510985 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.3312. Min Act: -0.1700
Data Index: 1465109 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.2999. Min Act: -0.1700
Data Index: 3787095 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.2999. Min Act: -0.1700
Data Index: 6680035 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.2374. Min Act: -0.1700
Data Index: 4465487 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.2062. Min Act: -0.1700
Data Index: 7273669 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.2374. Min Act: -0.1700
Data Index: 5508242 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.1749. Min Act: -0.1700
Data Index: 874647 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.1749. Min Act: -0.1700
Data Index: 1897411 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.1749. Min Act: -0.1700
Data Index: 6779534 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.1749. Min Act: -0.1700
Data Index: 6842278 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.1749. Min Act: -0.1700
Data Index: 8310514 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7687. Min Range: -5.7687
Max Act: 5.1437. Min Act: -0.1700
Data Index: 4012137 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19