Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1321. Min Range: -4.1321
Max Act: 4.1321. Min Act: -0.1700
Data Index: 1103993 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.7882. Min Act: -0.1700
Data Index: 8399959 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.7100. Min Act: -0.1700
Data Index: 888528 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.6162. Min Act: -0.1700
Data Index: 4685911 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.5849. Min Act: -0.1700
Data Index: 5676279 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.6162. Min Act: -0.1700
Data Index: 569439 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.5692. Min Act: -0.1700
Data Index: 248791 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4909. Min Act: -0.1700
Data Index: 4509895 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4909. Min Act: -0.1700
Data Index: 1844475 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4909. Min Act: -0.1700
Data Index: 5632111 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4596. Min Act: -0.1700
Data Index: 3114119 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4753. Min Act: -0.1700
Data Index: 618292 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4126. Min Act: -0.1700
Data Index: 5806230 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4596. Min Act: -0.1700
Data Index: 3037300 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4439. Min Act: -0.1700
Data Index: 8143883 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4126. Min Act: -0.1700
Data Index: 8822851 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4439. Min Act: -0.1700
Data Index: 1904745 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.3812. Min Act: -0.1700
Data Index: 4647596 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.4126. Min Act: -0.1700
Data Index: 7278312 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1321. Min Range: -4.1321
Max Act: 3.3655. Min Act: -0.1700
Data Index: 5724035 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19