Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1143. Min Range: -5.1143
Max Act: 5.1143. Min Act: -0.1700
Data Index: 4559863 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1143. Min Range: -5.1143
Max Act: 5.0831. Min Act: -0.1700
Data Index: 2511664 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1143. Min Range: -5.1143
Max Act: 5.0518. Min Act: -0.1700
Data Index: 981654 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1143. Min Range: -5.1143
Max Act: 5.0518. Min Act: -0.1700
Data Index: 4905865 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.9893. Min Act: -0.1700
Data Index: 7981481 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1143. Min Range: -5.1143
Max Act: 5.0206. Min Act: -0.1700
Data Index: 8471021 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.9581. Min Act: -0.1700
Data Index: 5153813 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.9268. Min Act: -0.1700
Data Index: 7627824 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.9268. Min Act: -0.1700
Data Index: 1306181 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.9268. Min Act: -0.1700
Data Index: 2254479 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8643. Min Act: -0.1700
Data Index: 701676 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.9268. Min Act: -0.1700
Data Index: 7129509 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8956. Min Act: -0.1700
Data Index: 6805590 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1109649 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8643. Min Act: -0.1700
Data Index: 5271122 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8331. Min Act: -0.1700
Data Index: 7089477 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1049539 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1192691 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8331. Min Act: -0.1700
Data Index: 222187 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1143. Min Range: -5.1143
Max Act: 4.8643. Min Act: -0.1700
Data Index: 1837193 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19