Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5140 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.7942. Min Act: -0.1700
Data Index: 4647752 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.7630. Min Act: -0.1700
Data Index: 708437 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.7317. Min Act: -0.1700
Data Index: 5794652 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.7005. Min Act: -0.1700
Data Index: 236357 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.6692. Min Act: -0.1700
Data Index: 5125552 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.6067. Min Act: -0.1700
Data Index: 2555913 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.6067. Min Act: -0.1700
Data Index: 905402 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.6067. Min Act: -0.1700
Data Index: 3287601 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.5755. Min Act: -0.1700
Data Index: 5863305 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.6380. Min Act: -0.1700
Data Index: 1107206 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.5755. Min Act: -0.1700
Data Index: 7884501 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.5442. Min Act: -0.1700
Data Index: 5131477 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.5755. Min Act: -0.1700
Data Index: 4120488 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.5755. Min Act: -0.1700
Data Index: 1972590 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.5442. Min Act: -0.1700
Data Index: 4738497 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.5130. Min Act: -0.1700
Data Index: 4027960 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.4192. Min Act: -0.1700
Data Index: 7041279 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.4192. Min Act: -0.1700
Data Index: 1068915 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.4192. Min Act: -0.1700
Data Index: 5275186 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7942. Min Range: -5.7942
Max Act: 5.4192. Min Act: -0.1700
Data Index: 2283271 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19