Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.2393. Min Act: -0.1700
Data Index: 7648197 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.1768. Min Act: -0.1700
Data Index: 8784558 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.1768. Min Act: -0.1700
Data Index: 5735727 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.1456. Min Act: -0.1700
Data Index: 5043562 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.1143. Min Act: -0.1700
Data Index: 5680384 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.0206. Min Act: -0.1700
Data Index: 3702901 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.0206. Min Act: -0.1700
Data Index: 607771 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.0206. Min Act: -0.1700
Data Index: 4361986 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2393. Min Range: -5.2393
Max Act: 5.0206. Min Act: -0.1700
Data Index: 5735728 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.9893. Min Act: -0.1700
Data Index: 482380 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.9581. Min Act: -0.1698
Data Index: 4643299 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.9581. Min Act: -0.1700
Data Index: 4643295 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.9581. Min Act: -0.1700
Data Index: 607777 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.8956. Min Act: -0.1700
Data Index: 2514076 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.8956. Min Act: -0.1700
Data Index: 4643289 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.8331. Min Act: -0.1700
Data Index: 2185423 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.8643. Min Act: -0.1700
Data Index: 6643761 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.8331. Min Act: -0.1700
Data Index: 607776 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.8331. Min Act: -0.1700
Data Index: 8610304 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2393. Min Range: -5.2393
Max Act: 4.8018. Min Act: -0.1700
Data Index: 7769527 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19