Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.8160. Min Act: -0.1700
Data Index: 3354542 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.7535. Min Act: -0.1700
Data Index: 1578129 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.5035. Min Act: -0.1700
Data Index: 365339 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3160. Min Act: -0.1700
Data Index: 1627439 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3160. Min Act: -0.1700
Data Index: 219200 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3160. Min Act: -0.1700
Data Index: 3008824 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2848. Min Act: -0.1700
Data Index: 3494479 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2848. Min Act: -0.1700
Data Index: 6691892 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2223. Min Act: -0.1700
Data Index: 8442415 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 192630 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1598. Min Act: -0.1700
Data Index: 6896327 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1598. Min Act: -0.1700
Data Index: 8639984 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1598. Min Act: -0.1700
Data Index: 2917150 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1598. Min Act: -0.1700
Data Index: 5317506 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1285. Min Act: -0.1700
Data Index: 6640258 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.0973. Min Act: -0.1700
Data Index: 6227147 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.0973. Min Act: -0.1700
Data Index: 4672541 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.0660. Min Act: -0.1700
Data Index: 2578303 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.0973. Min Act: -0.1700
Data Index: 2535399 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.0660. Min Act: -0.1700
Data Index: 5388635 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19