Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3515. Min Range: -7.3515
Max Act: 7.3515. Min Act: -0.1700
Data Index: 5057420 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3515. Min Range: -7.3515
Max Act: 7.1952. Min Act: -0.1700
Data Index: 6045067 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3515. Min Range: -7.3515
Max Act: 7.1952. Min Act: -0.1700
Data Index: 3367723 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3515. Min Range: -7.3515
Max Act: 7.1327. Min Act: -0.1700
Data Index: 5922480 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3515. Min Range: -7.3515
Max Act: 7.0390. Min Act: -0.1700
Data Index: 2480783 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3515. Min Range: -7.3515
Max Act: 7.0077. Min Act: -0.1700
Data Index: 1833284 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.9765. Min Act: -0.1700
Data Index: 5818358 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.9765. Min Act: -0.1700
Data Index: 7214282 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.9765. Min Act: -0.1700
Data Index: 888163 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.9765. Min Act: -0.1700
Data Index: 7475893 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8827. Min Act: -0.1700
Data Index: 3320341 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8827. Min Act: -0.1700
Data Index: 2539716 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8515. Min Act: -0.1700
Data Index: 7758542 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8827. Min Act: -0.1700
Data Index: 1460734 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8515. Min Act: -0.1700
Data Index: 4350884 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8515. Min Act: -0.1700
Data Index: 2692240 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8515. Min Act: -0.1700
Data Index: 2094735 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8202. Min Act: -0.1700
Data Index: 843671 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8202. Min Act: -0.1700
Data Index: 5094188 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3515. Min Range: -7.3515
Max Act: 6.8202. Min Act: -0.1700
Data Index: 1503510 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19