Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.3272. Min Act: -0.1700
Data Index: 7335253 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.3584. Min Act: -0.1700
Data Index: 511217 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.2334. Min Act: -0.1700
Data Index: 1982900 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.2022. Min Act: -0.1700
Data Index: 5162851 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.2334. Min Act: -0.1700
Data Index: 4265896 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.2334. Min Act: -0.1700
Data Index: 4357953 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1709. Min Act: -0.1700
Data Index: 1702068 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.2022. Min Act: -0.1700
Data Index: 1395331 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1397. Min Act: -0.1700
Data Index: 1372440 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1397. Min Act: -0.1700
Data Index: 109859 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1397. Min Act: -0.1700
Data Index: 6688681 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1709. Min Act: -0.1700
Data Index: 1054420 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1084. Min Act: -0.1700
Data Index: 6001669 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.0772. Min Act: -0.1700
Data Index: 660830 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1084. Min Act: -0.1700
Data Index: 146065 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1084. Min Act: -0.1700
Data Index: 7191733 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.0772. Min Act: -0.1700
Data Index: 2625984 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.1084. Min Act: -0.1700
Data Index: 8246773 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.0459. Min Act: -0.1700
Data Index: 4928295 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3584. Min Range: -7.3584
Max Act: 7.0459. Min Act: -0.1700
Data Index: 3205902 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19