Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0908. Min Range: -8.0908
Max Act: 8.0908. Min Act: -0.1700
Data Index: 1767931 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.5908. Min Act: -0.1700
Data Index: 3658163 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.4658. Min Act: -0.1700
Data Index: 4913135 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.5283. Min Act: -0.1700
Data Index: 6809439 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.4970. Min Act: -0.1700
Data Index: 5068173 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.4970. Min Act: -0.1700
Data Index: 3098517 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.4658. Min Act: -0.1700
Data Index: 1415371 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.4345. Min Act: -0.1700
Data Index: 5176900 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.3408. Min Act: -0.1700
Data Index: 6496857 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.3408. Min Act: -0.1700
Data Index: 397564 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.2783. Min Act: -0.1700
Data Index: 3624431 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.3408. Min Act: -0.1700
Data Index: 4994777 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.1533. Min Act: -0.1700
Data Index: 3460837 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.2470. Min Act: -0.1700
Data Index: 3095470 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.2783. Min Act: -0.1700
Data Index: 6995730 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.3095. Min Act: -0.1700
Data Index: 8485320 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.3095. Min Act: -0.1700
Data Index: 4554022 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.2783. Min Act: -0.1700
Data Index: 668046 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.3408. Min Act: -0.1700
Data Index: 7621719 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0908. Min Range: -8.0908
Max Act: 7.1220. Min Act: -0.1700
Data Index: 4487092 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19