Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.2432. Min Act: -0.1700
Data Index: 7534611 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.2119. Min Act: -0.1700
Data Index: 3176280 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.2119. Min Act: -0.1700
Data Index: 8723136 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.2119. Min Act: -0.1700
Data Index: 704667 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.1807. Min Act: -0.1700
Data Index: 543022 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.1182. Min Act: -0.1700
Data Index: 7853014 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.1494. Min Act: -0.1700
Data Index: 3316941 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.1182. Min Act: -0.1700
Data Index: 315064 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0869. Min Act: -0.1700
Data Index: 2751532 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0557. Min Act: -0.1700
Data Index: 2553975 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0869. Min Act: -0.1700
Data Index: 7246719 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0869. Min Act: -0.1700
Data Index: 6336672 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.1182. Min Act: -0.1700
Data Index: 8578226 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0557. Min Act: -0.1700
Data Index: 6257966 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0557. Min Act: -0.1700
Data Index: 2097671 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0557. Min Act: -0.1700
Data Index: 7194781 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2432. Min Range: -5.2432
Max Act: 5.0244. Min Act: -0.1700
Data Index: 2926932 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2432. Min Range: -5.2432
Max Act: 4.9932. Min Act: -0.1700
Data Index: 3579465 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2432. Min Range: -5.2432
Max Act: 4.9932. Min Act: -0.1700
Data Index: 7171062 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2432. Min Range: -5.2432
Max Act: 4.9619. Min Act: -0.1700
Data Index: 7772208 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19