Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 399 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.3644. Min Act: -0.1698
Data Index: 4763096 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.3331. Min Act: -0.1644
Data Index: 4969500 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.3331. Min Act: -0.1700
Data Index: 3173063 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2706. Min Act: -0.1700
Data Index: 3102330 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2706. Min Act: -0.1700
Data Index: 3820543 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2706. Min Act: -0.1700
Data Index: 8758409 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2706. Min Act: -0.1694
Data Index: 8200818 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2394. Min Act: -0.1699
Data Index: 5788863 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2706. Min Act: -0.1700
Data Index: 764980 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2706. Min Act: -0.1700
Data Index: 250295 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2081. Min Act: -0.1700
Data Index: 1286467 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2394. Min Act: -0.1700
Data Index: 3971366 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2706. Min Act: -0.1700
Data Index: 6222602 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2394. Min Act: -0.1699
Data Index: 2611648 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2394. Min Act: -0.1700
Data Index: 1634240 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2394. Min Act: -0.1699
Data Index: 410171 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2394. Min Act: -0.1696
Data Index: 7719996 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2394. Min Act: -0.1699
Data Index: 5343907 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2081. Min Act: -0.1690
Data Index: 2138894 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3644. Min Range: -5.3644
Max Act: 5.2081. Min Act: -0.1700
Data Index: 2041991 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19