Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3737 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.6172. Min Act: -0.1700
Data Index: 8374487 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.4922. Min Act: -0.1700
Data Index: 1826276 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.4297. Min Act: -0.1700
Data Index: 8161984 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3984. Min Act: -0.1700
Data Index: 5147495 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3984. Min Act: -0.1700
Data Index: 2535237 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3984. Min Act: -0.1700
Data Index: 5801184 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3672. Min Act: -0.1700
Data Index: 540924 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3359. Min Act: -0.1700
Data Index: 1143322 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3359. Min Act: -0.1700
Data Index: 6565236 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3047. Min Act: -0.1700
Data Index: 6175339 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3047. Min Act: -0.1700
Data Index: 7187466 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3047. Min Act: -0.1700
Data Index: 1106701 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.3047. Min Act: -0.1700
Data Index: 5221204 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.2734. Min Act: -0.1700
Data Index: 3534625 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.2734. Min Act: -0.1700
Data Index: 1144809 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.2734. Min Act: -0.1700
Data Index: 1790961 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.2422. Min Act: -0.1700
Data Index: 8753459 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.2422. Min Act: -0.1700
Data Index: 1633205 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.2109. Min Act: -0.1700
Data Index: 7924277 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6172. Min Range: -4.6172
Max Act: 4.2109. Min Act: -0.1700
Data Index: 3788574 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19