Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.6661. Min Act: -0.1700
Data Index: 3224606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.6036. Min Act: -0.1700
Data Index: 619502 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5724. Min Act: -0.1700
Data Index: 1084227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5724. Min Act: -0.1700
Data Index: 5190279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5724. Min Act: -0.1700
Data Index: 6005448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5724. Min Act: -0.1700
Data Index: 3808491 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5411. Min Act: -0.1700
Data Index: 2693364 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5411. Min Act: -0.1700
Data Index: 3867237 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.5099. Min Act: -0.1700
Data Index: 2813112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4786. Min Act: -0.1700
Data Index: 4684953 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4786. Min Act: -0.1700
Data Index: 8632730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4786. Min Act: -0.1700
Data Index: 2660834 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4474. Min Act: -0.1700
Data Index: 6995352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 6829671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4786. Min Act: -0.1700
Data Index: 8065588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 8360774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 2974973 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.3849. Min Act: -0.1700
Data Index: 2849558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4474. Min Act: -0.1700
Data Index: 4561012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6661. Min Range: -4.6661
Max Act: 4.4161. Min Act: -0.1700
Data Index: 2116507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19