Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1860. Min Range: -6.1860
Max Act: 6.1860. Min Act: -0.1700
Data Index: 2637519 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1860. Min Range: -6.1860
Max Act: 6.1547. Min Act: -0.1700
Data Index: 6465670 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1860. Min Range: -6.1860
Max Act: 6.0610. Min Act: -0.1700
Data Index: 4028931 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1860. Min Range: -6.1860
Max Act: 6.0922. Min Act: -0.1700
Data Index: 368583 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.9985. Min Act: -0.1700
Data Index: 863976 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.9672. Min Act: -0.1700
Data Index: 3650467 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.9360. Min Act: -0.1700
Data Index: 7909281 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.9360. Min Act: -0.1700
Data Index: 2426254 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.9047. Min Act: -0.1700
Data Index: 1759677 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.9047. Min Act: -0.1700
Data Index: 7595173 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.9047. Min Act: -0.1700
Data Index: 4498241 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8735. Min Act: -0.1700
Data Index: 5044189 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8422. Min Act: -0.1700
Data Index: 5997689 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8422. Min Act: -0.1700
Data Index: 8062178 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8422. Min Act: -0.1700
Data Index: 1782582 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8422. Min Act: -0.1700
Data Index: 1275832 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8422. Min Act: -0.1700
Data Index: 6584428 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8110. Min Act: -0.1700
Data Index: 2574880 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8110. Min Act: -0.1700
Data Index: 5485185 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1860. Min Range: -6.1860
Max Act: 5.8110. Min Act: -0.1700
Data Index: 2913400 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19