Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.5041. Min Act: -0.1700
Data Index: 4043300 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.3791. Min Act: -0.1700
Data Index: 8359976 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.3479. Min Act: -0.1700
Data Index: 3808838 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2854. Min Act: -0.1700
Data Index: 1121870 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.3166. Min Act: -0.1700
Data Index: 5166428 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.3166. Min Act: -0.1700
Data Index: 7343703 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2541. Min Act: -0.1700
Data Index: 6493828 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2541. Min Act: -0.1700
Data Index: 7691111 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2541. Min Act: -0.1700
Data Index: 1553234 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2229. Min Act: -0.1700
Data Index: 1622823 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2229. Min Act: -0.1700
Data Index: 4356458 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2229. Min Act: -0.1700
Data Index: 8388446 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2229. Min Act: -0.1700
Data Index: 2739771 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1916. Min Act: -0.1700
Data Index: 5274875 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1916. Min Act: -0.1700
Data Index: 6435620 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1916. Min Act: -0.1700
Data Index: 1652216 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.2229. Min Act: -0.1700
Data Index: 424595 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1916. Min Act: -0.1700
Data Index: 1202544 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1604. Min Act: -0.1700
Data Index: 3934091 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5041. Min Range: -5.5041
Max Act: 5.1604. Min Act: -0.1700
Data Index: 4709295 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19