Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4168. Min Range: -7.4168
Max Act: 7.4168. Min Act: -0.1700
Data Index: 8825207 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4168. Min Range: -7.4168
Max Act: 7.2918. Min Act: -0.1700
Data Index: 3514403 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4168. Min Range: -7.4168
Max Act: 7.1981. Min Act: -0.1700
Data Index: 3762267 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4168. Min Range: -7.4168
Max Act: 7.1668. Min Act: -0.1700
Data Index: 1006518 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.7606. Min Act: -0.1700
Data Index: 3023784 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.7293. Min Act: -0.1700
Data Index: 4703025 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.6668. Min Act: -0.1700
Data Index: 3871676 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.6668. Min Act: -0.1700
Data Index: 6214130 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.6356. Min Act: -0.1700
Data Index: 1212161 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.6668. Min Act: -0.1700
Data Index: 1854921 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.6356. Min Act: -0.1700
Data Index: 1212172 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.6356. Min Act: -0.1700
Data Index: 8471274 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.6043. Min Act: -0.1700
Data Index: 4215282 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.5731. Min Act: -0.1700
Data Index: 7162104 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.5731. Min Act: -0.1700
Data Index: 6515139 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.5731. Min Act: -0.1700
Data Index: 5631700 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.5418. Min Act: -0.1700
Data Index: 7449025 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.5418. Min Act: -0.1700
Data Index: 3116879 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.5418. Min Act: -0.1700
Data Index: 8613816 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4168. Min Range: -7.4168
Max Act: 6.4793. Min Act: -0.1700
Data Index: 5908794 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19