Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2427 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.6503. Min Act: -0.1700
Data Index: 256609 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.4628. Min Act: -0.1700
Data Index: 8277672 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.3378. Min Act: -0.1700
Data Index: 6081238 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.3691. Min Act: -0.1700
Data Index: 3580437 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.3691. Min Act: -0.1700
Data Index: 3987466 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.3066. Min Act: -0.1700
Data Index: 932553 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.3378. Min Act: -0.1700
Data Index: 7894744 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.3066. Min Act: -0.1700
Data Index: 4558526 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.2753. Min Act: -0.1700
Data Index: 8234507 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.3066. Min Act: -0.1700
Data Index: 5098989 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.2753. Min Act: -0.1700
Data Index: 5965567 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.2440. Min Act: -0.1700
Data Index: 3993367 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.2440. Min Act: -0.1700
Data Index: 1095925 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.2440. Min Act: -0.1700
Data Index: 6296545 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.2128. Min Act: -0.1700
Data Index: 4170319 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.1815. Min Act: -0.1700
Data Index: 2642483 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.2128. Min Act: -0.1700
Data Index: 6934139 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.1815. Min Act: -0.1700
Data Index: 2358921 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.1815. Min Act: -0.1700
Data Index: 1827979 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6503. Min Range: -4.6503
Max Act: 4.1815. Min Act: -0.1700
Data Index: 1883644 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19