Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.7689. Min Act: -0.1700
Data Index: 7384255 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.7689. Min Act: -0.1700
Data Index: 6628744 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.6751. Min Act: -0.1700
Data Index: 7029013 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.6751. Min Act: -0.1700
Data Index: 1060545 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.6439. Min Act: -0.1700
Data Index: 5592366 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.6439. Min Act: -0.1700
Data Index: 8016926 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.6126. Min Act: -0.1700
Data Index: 6567571 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5814. Min Act: -0.1700
Data Index: 649159 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5814. Min Act: -0.1700
Data Index: 780402 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5814. Min Act: -0.1700
Data Index: 6705341 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5501. Min Act: -0.1700
Data Index: 2294497 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.6126. Min Act: -0.1700
Data Index: 6381302 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5814. Min Act: -0.1700
Data Index: 6734629 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5188. Min Act: -0.1700
Data Index: 503582 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5501. Min Act: -0.1700
Data Index: 3515645 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.4876. Min Act: -0.1700
Data Index: 1332289 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5188. Min Act: -0.1700
Data Index: 8523547 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.4876. Min Act: -0.1700
Data Index: 2344457 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.5188. Min Act: -0.1700
Data Index: 2639427 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7689. Min Range: -4.7689
Max Act: 4.4876. Min Act: -0.1700
Data Index: 2546254 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19