Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4981 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.6822. Min Act: -0.1699
Data Index: 6868162 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.4947. Min Act: -0.1700
Data Index: 7046479 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.4634. Min Act: -0.1700
Data Index: 1281362 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.3697. Min Act: -0.1700
Data Index: 6653036 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.3697. Min Act: -0.1700
Data Index: 2236757 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.3697. Min Act: -0.1698
Data Index: 5236124 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2759. Min Act: -0.1700
Data Index: 7589063 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2447. Min Act: -0.1700
Data Index: 3763400 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.2447. Min Act: -0.1700
Data Index: 1635456 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1822. Min Act: -0.1700
Data Index: 4478103 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1197. Min Act: -0.1700
Data Index: 6822898 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.1197. Min Act: -0.1700
Data Index: 6426262 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.0884. Min Act: -0.1700
Data Index: 1965636 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.0259. Min Act: -0.1700
Data Index: 5790374 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6822. Min Range: -5.6822
Max Act: 5.0259. Min Act: -0.1699
Data Index: 5346971 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6822. Min Range: -5.6822
Max Act: 4.9947. Min Act: -0.1700
Data Index: 1641272 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6822. Min Range: -5.6822
Max Act: 4.9322. Min Act: -0.1700
Data Index: 3762954 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6822. Min Range: -5.6822
Max Act: 4.9634. Min Act: -0.1700
Data Index: 6176150 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6822. Min Range: -5.6822
Max Act: 4.9634. Min Act: -0.1696
Data Index: 5105249 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6822. Min Range: -5.6822
Max Act: 4.9322. Min Act: -0.1700
Data Index: 6839676 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19