Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1559 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.9934. Min Act: -0.1700
Data Index: 6196040 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.7434. Min Act: -0.1700
Data Index: 454858 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6809. Min Act: -0.1700
Data Index: 5719431 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.8059. Min Act: -0.1700
Data Index: 4177178 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6809. Min Act: -0.1700
Data Index: 1043904 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6809. Min Act: -0.1700
Data Index: 5081191 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6184. Min Act: -0.1700
Data Index: 6934071 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6184. Min Act: -0.1700
Data Index: 1901094 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6184. Min Act: -0.1700
Data Index: 7269664 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6184. Min Act: -0.1700
Data Index: 8192631 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.5559. Min Act: -0.1700
Data Index: 6016116 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.6184. Min Act: -0.1700
Data Index: 310819 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.5559. Min Act: -0.1700
Data Index: 1246346 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.4934. Min Act: -0.1700
Data Index: 7454118 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.4309. Min Act: -0.1700
Data Index: 1615994 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.4934. Min Act: -0.1700
Data Index: 5207628 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.5559. Min Act: -0.1700
Data Index: 3710681 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.4934. Min Act: -0.1700
Data Index: 3151081 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.4309. Min Act: -0.1700
Data Index: 6450971 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9934. Min Range: -8.9934
Max Act: 8.4309. Min Act: -0.1700
Data Index: 5383240 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19