Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2208 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.9833. Min Act: -0.1700
Data Index: 3715192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.9664. Min Act: -0.1700
Data Index: 1382688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.9154. Min Act: -0.1700
Data Index: 5612117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.9154. Min Act: -0.1699
Data Index: 2505797 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8727. Min Act: -0.1700
Data Index: 5505111 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8642. Min Act: -0.1700
Data Index: 5496032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8471. Min Act: -0.1700
Data Index: 975847 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8385. Min Act: -0.1700
Data Index: 2243857 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8385. Min Act: -0.1700
Data Index: 3778887 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8385. Min Act: -0.1700
Data Index: 3683807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8299. Min Act: -0.1700
Data Index: 8501210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8213. Min Act: -0.1700
Data Index: 8791763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8299. Min Act: -0.1700
Data Index: 4419671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.7956. Min Act: -0.1692
Data Index: 2916225 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8042. Min Act: -0.1700
Data Index: 2605243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8042. Min Act: -0.1698
Data Index: 6110527 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8042. Min Act: -0.1700
Data Index: 2298591 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.8042. Min Act: -0.1700
Data Index: 3651141 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.7869. Min Act: -0.1700
Data Index: 555005 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9833. Min Range: -1.9833
Max Act: 1.7783. Min Act: -0.1700
Data Index: 1464072 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19