Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1993 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.8619. Min Act: -0.1700
Data Index: 1196479 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.6431. Min Act: -0.1700
Data Index: 3852007 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.2369. Min Act: -0.1700
Data Index: 3387861 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.1431. Min Act: -0.1700
Data Index: 6328321 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.1119. Min Act: -0.1700
Data Index: 5489912 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.1119. Min Act: -0.1700
Data Index: 4717584 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.1119. Min Act: -0.1700
Data Index: 5323263 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 4996437 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 7934588 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 933963 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 2157027 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 7319273 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.0181. Min Act: -0.1700
Data Index: 3387862 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8619. Min Range: -5.8619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 1588560 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8619. Min Range: -5.8619
Max Act: 4.9869. Min Act: -0.1700
Data Index: 2927119 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8619. Min Range: -5.8619
Max Act: 4.9869. Min Act: -0.1700
Data Index: 5056164 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8619. Min Range: -5.8619
Max Act: 4.9869. Min Act: -0.1700
Data Index: 949695 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8619. Min Range: -5.8619
Max Act: 4.9556. Min Act: -0.1700
Data Index: 3314574 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8619. Min Range: -5.8619
Max Act: 4.9244. Min Act: -0.1700
Data Index: 861030 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8619. Min Range: -5.8619
Max Act: 4.9244. Min Act: -0.1700
Data Index: 841504 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19