Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0591. Min Act: -0.1700
Data Index: 7223328 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0423. Min Act: -0.1700
Data Index: 6401468 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0255. Min Act: -0.1700
Data Index: 8605395 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0423. Min Act: -0.1700
Data Index: 6701211 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0255. Min Act: -0.1700
Data Index: 2793915 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0423. Min Act: -0.1700
Data Index: 3890059 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0086. Min Act: -0.1700
Data Index: 1315900 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0086. Min Act: -0.1700
Data Index: 4765210 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0086. Min Act: -0.1700
Data Index: 3773913 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0086. Min Act: -0.1700
Data Index: 654009 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0086. Min Act: -0.1700
Data Index: 6374852 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0086. Min Act: -0.1700
Data Index: 2203368 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0591. Min Range: -2.0591
Max Act: 2.0086. Min Act: -0.1700
Data Index: 5869945 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0591. Min Range: -2.0591
Max Act: 1.9748. Min Act: -0.1700
Data Index: 6401087 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0591. Min Range: -2.0591
Max Act: 1.9748. Min Act: -0.1700
Data Index: 2367338 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0591. Min Range: -2.0591
Max Act: 1.9917. Min Act: -0.1700
Data Index: 5468333 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0591. Min Range: -2.0591
Max Act: 1.9748. Min Act: -0.1700
Data Index: 6797613 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0591. Min Range: -2.0591
Max Act: 1.9917. Min Act: -0.1700
Data Index: 4466914 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0591. Min Range: -2.0591
Max Act: 1.9917. Min Act: -0.1700
Data Index: 1404551 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0591. Min Range: -2.0591
Max Act: 1.9917. Min Act: -0.1700
Data Index: 5202826 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19