Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 742 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2782. Min Range: -6.2782
Max Act: 6.2782. Min Act: -0.1700
Data Index: 8315182 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2782. Min Range: -6.2782
Max Act: 6.2782. Min Act: -0.1700
Data Index: 6365152 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2782. Min Range: -6.2782
Max Act: 6.2157. Min Act: -0.1700
Data Index: 911991 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2782. Min Range: -6.2782
Max Act: 6.2157. Min Act: -0.1700
Data Index: 7727575 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2782. Min Range: -6.2782
Max Act: 6.1532. Min Act: -0.1700
Data Index: 8315186 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2782. Min Range: -6.2782
Max Act: 6.1532. Min Act: -0.1700
Data Index: 7969148 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2782. Min Range: -6.2782
Max Act: 6.0907. Min Act: -0.1700
Data Index: 7169269 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9970. Min Act: -0.1700
Data Index: 1415143 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9345. Min Act: -0.1700
Data Index: 5979088 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9345. Min Act: -0.1700
Data Index: 4446815 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9032. Min Act: -0.1700
Data Index: 1859014 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9345. Min Act: -0.1699
Data Index: 1242921 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9032. Min Act: -0.1700
Data Index: 2016941 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9032. Min Act: -0.1700
Data Index: 1236162 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.9345. Min Act: -0.1700
Data Index: 8586930 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.8095. Min Act: -0.1700
Data Index: 833632 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.8407. Min Act: -0.1700
Data Index: 8776049 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.8407. Min Act: -0.1700
Data Index: 6730833 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.8720. Min Act: -0.1700
Data Index: 2884526 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2782. Min Range: -6.2782
Max Act: 5.8720. Min Act: -0.1700
Data Index: 296338 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19