Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.8781. Min Act: -0.1699
Data Index: 2734776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.8438. Min Act: -0.1700
Data Index: 6245161 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.7923. Min Act: -0.1700
Data Index: 7327955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.8009. Min Act: -0.1700
Data Index: 1392271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.7492. Min Act: -0.1700
Data Index: 2080349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.7319. Min Act: -0.1700
Data Index: 1392273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.7146. Min Act: -0.1700
Data Index: 87750 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.7059. Min Act: -0.1700
Data Index: 5503011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6799. Min Act: -0.1700
Data Index: 7497279 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6886. Min Act: -0.1693
Data Index: 1392281 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6799. Min Act: -0.1700
Data Index: 3493000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6799. Min Act: -0.1700
Data Index: 4726730 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6712. Min Act: -0.1700
Data Index: 3463612 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6799. Min Act: -0.1700
Data Index: 2240878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6799. Min Act: -0.1700
Data Index: 2150681 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6886. Min Act: -0.1700
Data Index: 2734778 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6712. Min Act: -0.1700
Data Index: 6846315 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6799. Min Act: -0.1696
Data Index: 5364397 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6625. Min Act: -0.1700
Data Index: 2314384 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8781. Min Range: -1.8781
Max Act: 1.6625. Min Act: -0.1699
Data Index: 5404147 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19