Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1343 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.5374. Min Act: -0.1700
Data Index: 6677732 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.5061. Min Act: -0.1700
Data Index: 2707185 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.4749. Min Act: -0.1700
Data Index: 7592979 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.4749. Min Act: -0.1700
Data Index: 6080333 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.4436. Min Act: -0.1700
Data Index: 6903601 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.4124. Min Act: -0.1700
Data Index: 379014 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.4124. Min Act: -0.1700
Data Index: 5326681 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.4436. Min Act: -0.1700
Data Index: 1586650 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.3811. Min Act: -0.1700
Data Index: 1553422 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.3499. Min Act: -0.1700
Data Index: 5657000 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.3499. Min Act: -0.1700
Data Index: 3173107 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2874. Min Act: -0.1700
Data Index: 1376325 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2249. Min Act: -0.1700
Data Index: 6141566 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2561. Min Act: -0.1700
Data Index: 3295284 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2561. Min Act: -0.1700
Data Index: 7117984 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2249. Min Act: -0.1700
Data Index: 8706449 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2249. Min Act: -0.1700
Data Index: 4082861 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2249. Min Act: -0.1700
Data Index: 2168551 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.2249. Min Act: -0.1700
Data Index: 1900206 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5374. Min Range: -4.5374
Max Act: 4.1936. Min Act: -0.1700
Data Index: 2803543 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19