Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3229 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.3638. Min Act: -0.1700
Data Index: 3771727 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.3951. Min Act: -0.1700
Data Index: 1795319 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.3326. Min Act: -0.1700
Data Index: 4808163 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.3326. Min Act: -0.1700
Data Index: 5341270 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.1763. Min Act: -0.1700
Data Index: 7302251 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.2076. Min Act: -0.1700
Data Index: 3227249 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.1138. Min Act: -0.1700
Data Index: 5368968 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.1138. Min Act: -0.1700
Data Index: 9224 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.1138. Min Act: -0.1700
Data Index: 5483294 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0826. Min Act: -0.1700
Data Index: 7080857 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0826. Min Act: -0.1700
Data Index: 8071333 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.1138. Min Act: -0.1700
Data Index: 6443619 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0513. Min Act: -0.1700
Data Index: 5661959 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0826. Min Act: -0.1700
Data Index: 5539307 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0826. Min Act: -0.1700
Data Index: 2392516 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0201. Min Act: -0.1700
Data Index: 8030515 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0201. Min Act: -0.1700
Data Index: 8827331 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0513. Min Act: -0.1700
Data Index: 6610818 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3951. Min Range: -5.3951
Max Act: 4.9888. Min Act: -0.1700
Data Index: 5182861 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3951. Min Range: -5.3951
Max Act: 5.0513. Min Act: -0.1700
Data Index: 3852239 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19