Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.1997. Min Act: -0.1700
Data Index: 8794474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.1368. Min Act: -0.1700
Data Index: 6804964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.1210. Min Act: -0.1700
Data Index: 6846261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0738. Min Act: -0.1700
Data Index: 8581342 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0580. Min Act: -0.1700
Data Index: 1659141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0580. Min Act: -0.1700
Data Index: 1525122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0580. Min Act: -0.1700
Data Index: 3170030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0580. Min Act: -0.1700
Data Index: 6568014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0580. Min Act: -0.1700
Data Index: 5720002 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0422. Min Act: -0.1700
Data Index: 3110337 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0264. Min Act: -0.1700
Data Index: 5499075 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5962636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0264. Min Act: -0.1700
Data Index: 3023419 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0106. Min Act: -0.1700
Data Index: 4118579 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0106. Min Act: -0.1700
Data Index: 4483042 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1997. Min Range: -3.1997
Max Act: 3.0106. Min Act: -0.1700
Data Index: 6764991 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1997. Min Range: -3.1997
Max Act: 2.9948. Min Act: -0.1700
Data Index: 5688868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1997. Min Range: -3.1997
Max Act: 2.9948. Min Act: -0.1700
Data Index: 8358698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1997. Min Range: -3.1997
Max Act: 2.9948. Min Act: -0.1700
Data Index: 5549792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1997. Min Range: -3.1997
Max Act: 2.9790. Min Act: -0.1700
Data Index: 7662338 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19