Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5951. Min Act: -0.1700
Data Index: 5898631 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5467. Min Act: -0.1700
Data Index: 5733797 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5628. Min Act: -0.1700
Data Index: 5246145 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.6112. Min Act: -0.1700
Data Index: 1798583 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5467. Min Act: -0.1700
Data Index: 4442510 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5628. Min Act: -0.1700
Data Index: 4061098 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5467. Min Act: -0.1700
Data Index: 4917621 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5305. Min Act: -0.1700
Data Index: 541680 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5305. Min Act: -0.1700
Data Index: 5953548 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5467. Min Act: -0.1700
Data Index: 375306 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5144. Min Act: -0.1700
Data Index: 3056437 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5144. Min Act: -0.1700
Data Index: 2697335 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5467. Min Act: -0.1700
Data Index: 150787 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5305. Min Act: -0.1700
Data Index: 1698446 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5305. Min Act: -0.1700
Data Index: 845742 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5144. Min Act: -0.1700
Data Index: 3687688 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.4982. Min Act: -0.1700
Data Index: 4769320 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5144. Min Act: -0.1700
Data Index: 1489255 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.4820. Min Act: -0.1700
Data Index: 2853780 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6112. Min Range: -2.6112
Max Act: 2.5144. Min Act: -0.1700
Data Index: 33341 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19