Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2594 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.8034. Min Act: -0.1700
Data Index: 8515714 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.7409. Min Act: -0.1700
Data Index: 6690762 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.7721. Min Act: -0.1700
Data Index: 5873874 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.7096. Min Act: -0.1700
Data Index: 1298593 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.7409. Min Act: -0.1700
Data Index: 2525131 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.7096. Min Act: -0.1700
Data Index: 7500907 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6783. Min Act: -0.1700
Data Index: 646943 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6470. Min Act: -0.1700
Data Index: 7860166 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6157. Min Act: -0.1700
Data Index: 1285105 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6470. Min Act: -0.1700
Data Index: 1870394 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6470. Min Act: -0.1700
Data Index: 659070 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6157. Min Act: -0.1700
Data Index: 3608266 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6157. Min Act: -0.1700
Data Index: 1800002 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6470. Min Act: -0.1700
Data Index: 8456745 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6470. Min Act: -0.1700
Data Index: 1680616 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6470. Min Act: -0.1700
Data Index: 5073840 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6157. Min Act: -0.1700
Data Index: 7132666 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.5844. Min Act: -0.1700
Data Index: 4053570 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6157. Min Act: -0.1700
Data Index: 6043236 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8034. Min Range: -3.8034
Max Act: 3.6157. Min Act: -0.1700
Data Index: 7086736 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19