Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 550 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0841. Min Range: -6.0841
Max Act: 6.0841. Min Act: -0.1700
Data Index: 4364569 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7716. Min Act: -0.1700
Data Index: 2071005 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.8029. Min Act: -0.1700
Data Index: 3999093 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7716. Min Act: -0.1700
Data Index: 8019674 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7716. Min Act: -0.1700
Data Index: 311259 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7404. Min Act: -0.1700
Data Index: 5566546 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7091. Min Act: -0.1700
Data Index: 2788310 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7716. Min Act: -0.1700
Data Index: 850057 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6779. Min Act: -0.1700
Data Index: 89518 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.7091. Min Act: -0.1700
Data Index: 755058 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6779. Min Act: -0.1700
Data Index: 5682090 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6154. Min Act: -0.1700
Data Index: 674974 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6466. Min Act: -0.1700
Data Index: 3134610 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6466. Min Act: -0.1700
Data Index: 1280324 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.6154. Min Act: -0.1700
Data Index: 6888189 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5529. Min Act: -0.1700
Data Index: 2030751 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5841. Min Act: -0.1700
Data Index: 6392822 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5841. Min Act: -0.1700
Data Index: 3726158 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5841. Min Act: -0.1700
Data Index: 4804101 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0841. Min Range: -6.0841
Max Act: 5.5841. Min Act: -0.1700
Data Index: 7717460 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19