Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 849 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4236. Min Range: -9.4236
Max Act: 9.4236. Min Act: -0.1700
Data Index: 924248 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4236. Min Range: -9.4236
Max Act: 9.2361. Min Act: -0.1700
Data Index: 2958092 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.9861. Min Act: -0.1700
Data Index: 777054 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.9861. Min Act: -0.1700
Data Index: 1624488 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.9236. Min Act: -0.1700
Data Index: 2515543 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.8611. Min Act: -0.1700
Data Index: 1757958 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.8611. Min Act: -0.1700
Data Index: 7620006 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.7361. Min Act: -0.1700
Data Index: 8038560 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.6736. Min Act: -0.1700
Data Index: 7608146 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.6736. Min Act: -0.1700
Data Index: 7726952 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.6736. Min Act: -0.1700
Data Index: 2106363 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.6111. Min Act: -0.1700
Data Index: 2681184 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.5486. Min Act: -0.1700
Data Index: 1403319 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.5486. Min Act: -0.1700
Data Index: 5705498 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.4861. Min Act: -0.1700
Data Index: 2854529 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.4236. Min Act: -0.1700
Data Index: 4397124 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.4861. Min Act: -0.1700
Data Index: 8036726 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.4861. Min Act: -0.1700
Data Index: 7847836 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.4861. Min Act: -0.1700
Data Index: 5967620 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4236. Min Range: -9.4236
Max Act: 8.4861. Min Act: -0.1700
Data Index: 3225019 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19