Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.9306. Min Act: -0.1700
Data Index: 4547567 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.8681. Min Act: -0.1700
Data Index: 1019244 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.8681. Min Act: -0.1700
Data Index: 5668458 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.8368. Min Act: -0.1700
Data Index: 5493373 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.8056. Min Act: -0.1700
Data Index: 4547569 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.7431. Min Act: -0.1700
Data Index: 4547575 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.7431. Min Act: -0.1700
Data Index: 6320480 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.7431. Min Act: -0.1700
Data Index: 5937377 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.7118. Min Act: -0.1700
Data Index: 5382148 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6806. Min Act: -0.1700
Data Index: 2136756 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6493. Min Act: -0.1700
Data Index: 4004522 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6493. Min Act: -0.1700
Data Index: 8087505 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6806. Min Act: -0.1700
Data Index: 2497119 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6493. Min Act: -0.1700
Data Index: 1261142 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6493. Min Act: -0.1700
Data Index: 6320475 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6806. Min Act: -0.1700
Data Index: 166770 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1462017 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6181. Min Act: -0.1700
Data Index: 5874974 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1451 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9306. Min Range: -5.9306
Max Act: 5.5868. Min Act: -0.1700
Data Index: 417315 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19