Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1161 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0716. Min Range: -2.0716
Max Act: 2.0716. Min Act: -0.1700
Data Index: 231775 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.9788. Min Act: -0.1700
Data Index: 2524684 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.9534. Min Act: -0.1700
Data Index: 11709 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8768. Min Act: -0.1700
Data Index: 3901665 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.9449. Min Act: -0.1700
Data Index: 7805304 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8768. Min Act: -0.1700
Data Index: 7180830 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8939. Min Act: -0.1700
Data Index: 5782919 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8511. Min Act: -0.1700
Data Index: 3980283 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8853. Min Act: -0.1700
Data Index: 8210386 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8425. Min Act: -0.1700
Data Index: 1084056 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8511. Min Act: -0.1700
Data Index: 429286 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8425. Min Act: -0.1700
Data Index: 91620 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8340. Min Act: -0.1700
Data Index: 8332777 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8511. Min Act: -0.1700
Data Index: 550106 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8340. Min Act: -0.1700
Data Index: 336888 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8340. Min Act: -0.1700
Data Index: 4354031 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8425. Min Act: -0.1700
Data Index: 1693936 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8254. Min Act: -0.1700
Data Index: 5432582 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8082. Min Act: -0.1700
Data Index: 1620882 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0716. Min Range: -2.0716
Max Act: 1.8682. Min Act: -0.1700
Data Index: 3929955 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19