Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.2915. Min Act: -0.1700
Data Index: 1117099 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.2290. Min Act: -0.1700
Data Index: 7756262 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.1353. Min Act: -0.1700
Data Index: 4844333 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.1040. Min Act: -0.1700
Data Index: 1668621 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.0728. Min Act: -0.1700
Data Index: 2673210 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2915. Min Range: -7.2915
Max Act: 7.0103. Min Act: -0.1700
Data Index: 1874679 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.9478. Min Act: -0.1700
Data Index: 6553105 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.9478. Min Act: -0.1700
Data Index: 7955846 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.8853. Min Act: -0.1700
Data Index: 3041208 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.8228. Min Act: -0.1700
Data Index: 2161123 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.8228. Min Act: -0.1700
Data Index: 1204377 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.8228. Min Act: -0.1700
Data Index: 591410 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7915. Min Act: -0.1700
Data Index: 7537275 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7915. Min Act: -0.1700
Data Index: 6489674 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.8228. Min Act: -0.1700
Data Index: 2753076 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7915. Min Act: -0.1700
Data Index: 8595935 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7603. Min Act: -0.1700
Data Index: 8300721 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7290. Min Act: -0.1700
Data Index: 6692346 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7290. Min Act: -0.1700
Data Index: 6523585 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2915. Min Range: -7.2915
Max Act: 6.7290. Min Act: -0.1700
Data Index: 5022374 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19