Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.2425. Min Range: -6.2425
Max Act: 6.2425. Min Act: -0.1700
Data Index: 1777909 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.8988. Min Act: -0.1700
Data Index: 6398619 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.6800. Min Act: -0.1700
Data Index: 2637606 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.6488. Min Act: -0.1700
Data Index: 1422740 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2425. Min Range: -6.2425
Max Act: 4.6175. Min Act: -0.1700
Data Index: 6233993 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2425. Min Range: -6.2425
Max Act: 4.4300. Min Act: -0.1700
Data Index: 7790409 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2425. Min Range: -6.2425
Max Act: 4.3363. Min Act: -0.1700
Data Index: 6519713 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.5863. Min Act: -0.1700
Data Index: 207378 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.2113. Min Act: -0.1700
Data Index: 1863107 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.4925. Min Act: -0.1700
Data Index: 5919315 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.2113. Min Act: -0.1700
Data Index: 4045189 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.3988. Min Act: -0.1700
Data Index: 3943527 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2425. Min Range: -6.2425
Max Act: 4.5238. Min Act: -0.1700
Data Index: 1310402 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.3050. Min Act: -0.1699
Data Index: 4848497 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.3050. Min Act: -0.1700
Data Index: 5502647 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.3363. Min Act: -0.1700
Data Index: 8673296 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.0550. Min Act: -0.1700
Data Index: 4169526 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.3363. Min Act: -0.1700
Data Index: 5733701 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2425. Min Range: -6.2425
Max Act: 5.3988. Min Act: -0.1700
Data Index: 7465794 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2425. Min Range: -6.2425
Max Act: 3.8830. Min Act: -0.1700
Data Index: 1761864 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19