Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2131. Min Range: -8.2131
Max Act: 8.2131. Min Act: -0.1700
Data Index: 432555 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.8381. Min Act: -0.1700
Data Index: 7087286 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.7444. Min Act: -0.1700
Data Index: 4233213 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.6506. Min Act: -0.1700
Data Index: 487969 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.6194. Min Act: -0.1700
Data Index: 3980947 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5881. Min Act: -0.1700
Data Index: 5868894 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5569. Min Act: -0.1700
Data Index: 2210350 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 2902716 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5569. Min Act: -0.1700
Data Index: 2843167 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 7389009 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 1848865 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 1131346 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.4944. Min Act: -0.1700
Data Index: 990833 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.5256. Min Act: -0.1700
Data Index: 714319 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.4319. Min Act: -0.1700
Data Index: 4293945 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.4631. Min Act: -0.1700
Data Index: 740197 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.4006. Min Act: -0.1700
Data Index: 4793037 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.3694. Min Act: -0.1700
Data Index: 2398163 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.3381. Min Act: -0.1700
Data Index: 5292662 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2131. Min Range: -8.2131
Max Act: 7.3381. Min Act: -0.1700
Data Index: 4530624 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19