Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.4587. Min Act: -0.1700
Data Index: 4877617 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.4274. Min Act: -0.1700
Data Index: 4145054 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.4274. Min Act: -0.1700
Data Index: 1566130 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 3264231 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3962. Min Act: -0.1700
Data Index: 6851259 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3962. Min Act: -0.1700
Data Index: 3951384 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1699
Data Index: 1601099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 231142 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 4147592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 8669740 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 6058586 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 3279789 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 2645432 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 342245 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 6186431 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3337. Min Act: -0.1698
Data Index: 1223249 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3337. Min Act: -0.1700
Data Index: 2011448 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 1043649 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3649. Min Act: -0.1700
Data Index: 3245744 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4587. Min Range: -4.4587
Max Act: 4.3337. Min Act: -0.1700
Data Index: 5882692 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19