Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1400 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.1908. Min Act: -0.1700
Data Index: 1309254 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.1594. Min Act: -0.1700
Data Index: 6211691 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.1751. Min Act: -0.1700
Data Index: 6572163 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.1279. Min Act: -0.1700
Data Index: 5663454 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.1279. Min Act: -0.1700
Data Index: 5261487 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0491. Min Act: -0.1700
Data Index: 5378588 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.1279. Min Act: -0.1700
Data Index: 5924213 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0806. Min Act: -0.1700
Data Index: 485606 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0806. Min Act: -0.1700
Data Index: 2823399 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0648. Min Act: -0.1700
Data Index: 8747704 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0648. Min Act: -0.1700
Data Index: 6697072 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0491. Min Act: -0.1700
Data Index: 5828972 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0491. Min Act: -0.1700
Data Index: 753754 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0333. Min Act: -0.1700
Data Index: 4468342 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0806. Min Act: -0.1700
Data Index: 4509977 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0017. Min Act: -0.1700
Data Index: 8550820 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0333. Min Act: -0.1700
Data Index: 4718617 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0175. Min Act: -0.1697
Data Index: 3461319 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0175. Min Act: -0.1700
Data Index: 4704943 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1908. Min Range: -3.1908
Max Act: 3.0175. Min Act: -0.1700
Data Index: 5923354 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19