Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.9599. Min Act: -0.1700
Data Index: 1776244 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.8036. Min Act: -0.1700
Data Index: 8805073 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.6474. Min Act: -0.1700
Data Index: 3731595 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.3974. Min Act: -0.1700
Data Index: 4193747 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.3974. Min Act: -0.1700
Data Index: 502746 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.3349. Min Act: -0.1700
Data Index: 3035680 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.3036. Min Act: -0.1700
Data Index: 28711 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.2411. Min Act: -0.1700
Data Index: 6035688 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.2099. Min Act: -0.1700
Data Index: 1193559 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.1786. Min Act: -0.1700
Data Index: 654242 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.1786. Min Act: -0.1700
Data Index: 3345807 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.1474. Min Act: -0.1700
Data Index: 6640718 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.1161. Min Act: -0.1700
Data Index: 7676606 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.1474. Min Act: -0.1700
Data Index: 6045349 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.0849. Min Act: -0.1700
Data Index: 2278168 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.0536. Min Act: -0.1700
Data Index: 5332781 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9599. Min Range: -6.9599
Max Act: 5.9911. Min Act: -0.1700
Data Index: 666798 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.0536. Min Act: -0.1700
Data Index: 3419215 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9599. Min Range: -6.9599
Max Act: 6.0224. Min Act: -0.1700
Data Index: 1541567 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9599. Min Range: -6.9599
Max Act: 5.9911. Min Act: -0.1700
Data Index: 5054430 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19