Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 822 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6522. Min Range: -8.6522
Max Act: 8.6522. Min Act: -0.1700
Data Index: 8060958 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6522. Min Range: -8.6522
Max Act: 8.4647. Min Act: -0.1700
Data Index: 5504149 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.9022. Min Act: -0.1700
Data Index: 2364127 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.9647. Min Act: -0.1700
Data Index: 8060957 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.9022. Min Act: -0.1700
Data Index: 7839434 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.9022. Min Act: -0.1700
Data Index: 658997 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.8397. Min Act: -0.1700
Data Index: 8486971 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.8397. Min Act: -0.1700
Data Index: 5039595 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.8085. Min Act: -0.1700
Data Index: 1777994 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.7460. Min Act: -0.1700
Data Index: 2060248 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.7147. Min Act: -0.1700
Data Index: 5784555 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.7147. Min Act: -0.1700
Data Index: 8327112 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.6522. Min Act: -0.1700
Data Index: 1846569 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.6835. Min Act: -0.1700
Data Index: 2457081 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.6522. Min Act: -0.1700
Data Index: 658995 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.6522. Min Act: -0.1700
Data Index: 481554 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.6210. Min Act: -0.1700
Data Index: 898952 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.5897. Min Act: -0.1700
Data Index: 6800614 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.5897. Min Act: -0.1700
Data Index: 8060955 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6522. Min Range: -8.6522
Max Act: 7.5897. Min Act: -0.1700
Data Index: 4040501 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19