Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.6921. Min Act: -0.1700
Data Index: 4876814 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.5983. Min Act: -0.1700
Data Index: 6817846 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.4416. Min Act: -0.1700
Data Index: 1904777 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.4103. Min Act: -0.1700
Data Index: 2429383 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.4103. Min Act: -0.1700
Data Index: 223691 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3946. Min Act: -0.1700
Data Index: 3623085 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3476. Min Act: -0.1700
Data Index: 1839617 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3633. Min Act: -0.1700
Data Index: 3176425 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3476. Min Act: -0.1700
Data Index: 1942699 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3319. Min Act: -0.1700
Data Index: 8642011 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3162. Min Act: -0.1700
Data Index: 1522899 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3319. Min Act: -0.1700
Data Index: 4538477 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3162. Min Act: -0.1700
Data Index: 4775135 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3005. Min Act: -0.1700
Data Index: 1459754 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.2848. Min Act: -0.1700
Data Index: 7040150 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.2534. Min Act: -0.1700
Data Index: 4855341 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.2534. Min Act: -0.1700
Data Index: 5403852 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.3005. Min Act: -0.1700
Data Index: 3862887 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.2691. Min Act: -0.1700
Data Index: 2716682 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6921. Min Range: -3.6921
Max Act: 3.2691. Min Act: -0.1700
Data Index: 5413724 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19