Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1447 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0203. Min Range: -4.0203
Max Act: 4.0203. Min Act: -0.1700
Data Index: 83645 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.9265. Min Act: -0.1700
Data Index: 4597635 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.8640. Min Act: -0.1700
Data Index: 4396260 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.8014. Min Act: -0.1700
Data Index: 6894340 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7389. Min Act: -0.1700
Data Index: 4008749 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7702. Min Act: -0.1700
Data Index: 7060271 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7702. Min Act: -0.1700
Data Index: 4651913 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7702. Min Act: -0.1700
Data Index: 2353688 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7389. Min Act: -0.1700
Data Index: 4927941 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7389. Min Act: -0.1700
Data Index: 8801970 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7389. Min Act: -0.1700
Data Index: 3987928 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7389. Min Act: -0.1700
Data Index: 8401533 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.7389. Min Act: -0.1700
Data Index: 5682592 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.6450. Min Act: -0.1700
Data Index: 1357151 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.6763. Min Act: -0.1700
Data Index: 6209398 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.6763. Min Act: -0.1700
Data Index: 3003702 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.6450. Min Act: -0.1700
Data Index: 1647973 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.6763. Min Act: -0.1700
Data Index: 378645 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.6763. Min Act: -0.1700
Data Index: 44042 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0203. Min Range: -4.0203
Max Act: 3.6763. Min Act: -0.1700
Data Index: 4725480 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19