Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0337. Min Range: -4.0337
Max Act: 4.0337. Min Act: -0.1700
Data Index: 6266931 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0337. Min Range: -4.0337
Max Act: 4.0337. Min Act: -0.1700
Data Index: 7542539 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.9400. Min Act: -0.1700
Data Index: 198612 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.9400. Min Act: -0.1700
Data Index: 8341806 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8462. Min Act: -0.1700
Data Index: 1486404 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8462. Min Act: -0.1700
Data Index: 7717796 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8462. Min Act: -0.1700
Data Index: 3704408 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 6886838 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 5517964 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8462. Min Act: -0.1700
Data Index: 166273 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 102401 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.7836. Min Act: -0.1700
Data Index: 2425760 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 6059610 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.7836. Min Act: -0.1700
Data Index: 8450956 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 2178978 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 7848778 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.7836. Min Act: -0.1700
Data Index: 2952538 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 1527212 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8462. Min Act: -0.1700
Data Index: 4740887 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0337. Min Range: -4.0337
Max Act: 3.8149. Min Act: -0.1700
Data Index: 3322408 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19