Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.8776. Min Act: -0.1700
Data Index: 4692958 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.7839. Min Act: -0.1700
Data Index: 7044861 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.6589. Min Act: -0.1700
Data Index: 4987543 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.6589. Min Act: -0.1700
Data Index: 3871544 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.6901. Min Act: -0.1700
Data Index: 130086 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.6276. Min Act: -0.1700
Data Index: 7935338 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.6589. Min Act: -0.1700
Data Index: 2313237 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.6901. Min Act: -0.1700
Data Index: 7714155 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.5651. Min Act: -0.1700
Data Index: 413364 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.5651. Min Act: -0.1700
Data Index: 6260474 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.5651. Min Act: -0.1700
Data Index: 6392945 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.5339. Min Act: -0.1700
Data Index: 199871 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.5339. Min Act: -0.1700
Data Index: 5687195 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.5026. Min Act: -0.1700
Data Index: 3115150 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.5026. Min Act: -0.1700
Data Index: 2694547 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.4714. Min Act: -0.1700
Data Index: 998396 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.4714. Min Act: -0.1700
Data Index: 971615 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.4401. Min Act: -0.1700
Data Index: 3358879 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.4714. Min Act: -0.1700
Data Index: 2752396 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8776. Min Range: -5.8776
Max Act: 5.4401. Min Act: -0.1700
Data Index: 2778638 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19