Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1462 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.6651. Min Act: -0.1700
Data Index: 8072888 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.6495. Min Act: -0.1700
Data Index: 701989 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.6338. Min Act: -0.1700
Data Index: 7178765 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.6495. Min Act: -0.1700
Data Index: 5622725 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.6182. Min Act: -0.1700
Data Index: 994247 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.6025. Min Act: -0.1700
Data Index: 5202874 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5869. Min Act: -0.1700
Data Index: 5538357 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5555. Min Act: -0.1700
Data Index: 675140 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5555. Min Act: -0.1700
Data Index: 702527 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5399. Min Act: -0.1700
Data Index: 3601700 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5555. Min Act: -0.1700
Data Index: 6232325 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5399. Min Act: -0.1700
Data Index: 604059 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5399. Min Act: -0.1700
Data Index: 405625 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5242. Min Act: -0.1700
Data Index: 4696219 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.5242. Min Act: -0.1700
Data Index: 7933469 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.4929. Min Act: -0.1700
Data Index: 4476587 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.4772. Min Act: -0.1700
Data Index: 6005549 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.4929. Min Act: -0.1700
Data Index: 6382900 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.4929. Min Act: -0.1700
Data Index: 698597 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6651. Min Range: -3.6651
Max Act: 3.4772. Min Act: -0.1700
Data Index: 2017565 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19