Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.4527. Min Act: -0.1700
Data Index: 3307472 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.4214. Min Act: -0.1700
Data Index: 140352 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.3589. Min Act: -0.1700
Data Index: 4229937 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.3589. Min Act: -0.1700
Data Index: 4133152 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.3902. Min Act: -0.1700
Data Index: 6809221 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.3277. Min Act: -0.1700
Data Index: 1349929 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.3277. Min Act: -0.1700
Data Index: 1221833 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2964. Min Act: -0.1700
Data Index: 2888992 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.3277. Min Act: -0.1700
Data Index: 684272 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2964. Min Act: -0.1700
Data Index: 5516976 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2964. Min Act: -0.1700
Data Index: 6200586 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2339. Min Act: -0.1700
Data Index: 8178750 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2339. Min Act: -0.1700
Data Index: 1814527 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2339. Min Act: -0.1700
Data Index: 5218978 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2339. Min Act: -0.1700
Data Index: 7640073 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2339. Min Act: -0.1700
Data Index: 1767994 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2339. Min Act: -0.1700
Data Index: 6064139 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2027. Min Act: -0.1700
Data Index: 6514249 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2027. Min Act: -0.1700
Data Index: 296181 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4527. Min Range: -6.4527
Max Act: 6.2027. Min Act: -0.1700
Data Index: 5228974 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19