Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5904 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.7360. Min Act: -0.1700
Data Index: 5550148 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.7360. Min Act: -0.1700
Data Index: 3362398 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.6735. Min Act: -0.1700
Data Index: 1746898 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.6110. Min Act: -0.1700
Data Index: 4875599 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5797. Min Act: -0.1700
Data Index: 346458 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5797. Min Act: -0.1700
Data Index: 4873580 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5485. Min Act: -0.1700
Data Index: 4264497 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5485. Min Act: -0.1700
Data Index: 3471930 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5485. Min Act: -0.1700
Data Index: 2148498 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5172. Min Act: -0.1700
Data Index: 6005462 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5172. Min Act: -0.1700
Data Index: 6130980 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5172. Min Act: -0.1700
Data Index: 6747447 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5485. Min Act: -0.1700
Data Index: 6935447 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5172. Min Act: -0.1700
Data Index: 3009437 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5172. Min Act: -0.1700
Data Index: 1724358 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5172. Min Act: -0.1700
Data Index: 3498032 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.5172. Min Act: -0.1700
Data Index: 1594057 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.4860. Min Act: -0.1700
Data Index: 2925417 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.4547. Min Act: -0.1699
Data Index: 1180726 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7360. Min Range: -6.7360
Max Act: 6.4860. Min Act: -0.1700
Data Index: 3250592 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19