Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.6774. Min Act: -0.1700
Data Index: 2316063 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.5837. Min Act: -0.1700
Data Index: 6446908 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.4899. Min Act: -0.1700
Data Index: 3632537 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.4274. Min Act: -0.1700
Data Index: 1552433 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.3962. Min Act: -0.1700
Data Index: 5006706 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.3962. Min Act: -0.1700
Data Index: 4684613 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.3962. Min Act: -0.1700
Data Index: 3426592 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.3337. Min Act: -0.1700
Data Index: 2474705 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.3024. Min Act: -0.1700
Data Index: 597095 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.3337. Min Act: -0.1700
Data Index: 6948730 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.2712. Min Act: -0.1700
Data Index: 229316 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.2399. Min Act: -0.1700
Data Index: 601184 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.2399. Min Act: -0.1700
Data Index: 2322468 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.2087. Min Act: -0.1700
Data Index: 1714478 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.1774. Min Act: -0.1700
Data Index: 6163679 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.1774. Min Act: -0.1700
Data Index: 6075458 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.1774. Min Act: -0.1700
Data Index: 4301935 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.1462. Min Act: -0.1700
Data Index: 3920246 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.1462. Min Act: -0.1700
Data Index: 5653312 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6774. Min Range: -7.6774
Max Act: 7.1149. Min Act: -0.1700
Data Index: 3861775 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19