Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5091 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.5883. Min Act: -0.1700
Data Index: 2999146 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.5883. Min Act: -0.1700
Data Index: 8349227 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.5258. Min Act: -0.1700
Data Index: 748297 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.4946. Min Act: -0.1700
Data Index: 2531810 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.4633. Min Act: -0.1700
Data Index: 2351546 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.4321. Min Act: -0.1700
Data Index: 3617262 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.4008. Min Act: -0.1700
Data Index: 586455 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.3383. Min Act: -0.1700
Data Index: 6571838 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.3071. Min Act: -0.1700
Data Index: 2747204 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.2446. Min Act: -0.1700
Data Index: 7824939 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.2133. Min Act: -0.1700
Data Index: 3734124 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.2446. Min Act: -0.1700
Data Index: 2106370 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1821. Min Act: -0.1700
Data Index: 3005913 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1821. Min Act: -0.1700
Data Index: 4236722 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1508. Min Act: -0.1700
Data Index: 5019147 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1821. Min Act: -0.1700
Data Index: 2950976 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1508. Min Act: -0.1700
Data Index: 7679996 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1508. Min Act: -0.1700
Data Index: 6013096 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1508. Min Act: -0.1700
Data Index: 4227284 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5883. Min Range: -5.5883
Max Act: 5.1196. Min Act: -0.1700
Data Index: 6512379 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19