Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2349 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.4774. Min Act: -0.1700
Data Index: 4940396 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.4774. Min Act: -0.1700
Data Index: 7702093 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.2899. Min Act: -0.1700
Data Index: 5676157 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.2899. Min Act: -0.1700
Data Index: 5728298 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.2899. Min Act: -0.1700
Data Index: 6409450 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.2274. Min Act: -0.1700
Data Index: 36916 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.2899. Min Act: -0.1700
Data Index: 8059094 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.1649. Min Act: -0.1700
Data Index: 3919032 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.1962. Min Act: -0.1700
Data Index: 4949740 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.1337. Min Act: -0.1700
Data Index: 5441177 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.0712. Min Act: -0.1700
Data Index: 7965615 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.0087. Min Act: -0.1700
Data Index: 4570780 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.0399. Min Act: -0.1700
Data Index: 1402325 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.0399. Min Act: -0.1700
Data Index: 7575635 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.0399. Min Act: -0.1700
Data Index: 6504512 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4774. Min Range: -8.4774
Max Act: 7.9774. Min Act: -0.1700
Data Index: 4236942 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4774. Min Range: -8.4774
Max Act: 7.9774. Min Act: -0.1700
Data Index: 145742 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4774. Min Range: -8.4774
Max Act: 7.9774. Min Act: -0.1700
Data Index: 6540898 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4774. Min Range: -8.4774
Max Act: 8.0087. Min Act: -0.1700
Data Index: 7186593 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4774. Min Range: -8.4774
Max Act: 7.9774. Min Act: -0.1700
Data Index: 5387701 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19