Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.3483. Min Act: -0.1700
Data Index: 3366476 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.3483. Min Act: -0.1700
Data Index: 7219657 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.2384. Min Act: -0.1700
Data Index: 2932342 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.2069. Min Act: -0.1700
Data Index: 2433405 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.2227. Min Act: -0.1700
Data Index: 97006 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.2069. Min Act: -0.1700
Data Index: 5240176 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1912. Min Act: -0.1700
Data Index: 5240170 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1597. Min Act: -0.1700
Data Index: 3401919 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1755. Min Act: -0.1700
Data Index: 54159 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1597. Min Act: -0.1700
Data Index: 3455562 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1597. Min Act: -0.1700
Data Index: 2085664 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1597. Min Act: -0.1700
Data Index: 8203400 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1440. Min Act: -0.1700
Data Index: 54163 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1125. Min Act: -0.1700
Data Index: 7905710 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1125. Min Act: -0.1700
Data Index: 1065390 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1125. Min Act: -0.1700
Data Index: 2232785 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1125. Min Act: -0.1700
Data Index: 1568921 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1125. Min Act: -0.1700
Data Index: 327013 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.1125. Min Act: -0.1700
Data Index: 782888 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3483. Min Range: -3.3483
Max Act: 3.0967. Min Act: -0.1700
Data Index: 7335729 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19