Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2167. Min Range: -5.2167
Max Act: 5.2167. Min Act: -0.1700
Data Index: 7916730 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2167. Min Range: -5.2167
Max Act: 5.1230. Min Act: -0.1700
Data Index: 3758277 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2167. Min Range: -5.2167
Max Act: 5.0917. Min Act: -0.1700
Data Index: 3641567 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2167. Min Range: -5.2167
Max Act: 5.0605. Min Act: -0.1700
Data Index: 7675320 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9980. Min Act: -0.1700
Data Index: 6547301 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9980. Min Act: -0.1700
Data Index: 7369820 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9980. Min Act: -0.1700
Data Index: 3036607 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9667. Min Act: -0.1700
Data Index: 4679515 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9667. Min Act: -0.1700
Data Index: 7126661 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9042. Min Act: -0.1700
Data Index: 4830910 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8730. Min Act: -0.1700
Data Index: 7456940 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9042. Min Act: -0.1700
Data Index: 7770104 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.9042. Min Act: -0.1700
Data Index: 3607503 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8730. Min Act: -0.1700
Data Index: 2230805 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8730. Min Act: -0.1700
Data Index: 7607180 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8417. Min Act: -0.1700
Data Index: 7353715 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8417. Min Act: -0.1700
Data Index: 8758617 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8417. Min Act: -0.1700
Data Index: 2649052 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8105. Min Act: -0.1700
Data Index: 2831002 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2167. Min Range: -5.2167
Max Act: 4.8105. Min Act: -0.1700
Data Index: 3558117 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19