Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.4662. Min Act: -0.1700
Data Index: 2911986 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.4350. Min Act: -0.1700
Data Index: 4932193 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.3100. Min Act: -0.1700
Data Index: 4850026 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.3100. Min Act: -0.1700
Data Index: 1399233 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.2787. Min Act: -0.1700
Data Index: 2177762 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.2162. Min Act: -0.1700
Data Index: 8475713 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1537. Min Act: -0.1700
Data Index: 891799 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1537. Min Act: -0.1700
Data Index: 5166139 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0912. Min Act: -0.1700
Data Index: 7539416 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0600. Min Act: -0.1700
Data Index: 2801388 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0912. Min Act: -0.1700
Data Index: 5326055 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.1225. Min Act: -0.1700
Data Index: 5490933 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0912. Min Act: -0.1700
Data Index: 8492726 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0600. Min Act: -0.1700
Data Index: 2086080 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0600. Min Act: -0.1700
Data Index: 4605093 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0600. Min Act: -0.1700
Data Index: 306124 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0287. Min Act: -0.1700
Data Index: 7820135 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0600. Min Act: -0.1700
Data Index: 3699377 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0600. Min Act: -0.1700
Data Index: 5891549 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4662. Min Range: -5.4662
Max Act: 5.0287. Min Act: -0.1700
Data Index: 8055069 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19