Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 786 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.9492. Min Act: -0.1700
Data Index: 7506580 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.9492. Min Act: -0.1700
Data Index: 5562070 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.9179. Min Act: -0.1700
Data Index: 8166068 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.9179. Min Act: -0.1700
Data Index: 3112991 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.9179. Min Act: -0.1700
Data Index: 4165718 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8554. Min Act: -0.1700
Data Index: 7222355 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8867. Min Act: -0.1699
Data Index: 654191 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8867. Min Act: -0.1700
Data Index: 4580695 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8242. Min Act: -0.1700
Data Index: 705869 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8554. Min Act: -0.1700
Data Index: 3064470 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8554. Min Act: -0.1700
Data Index: 4059481 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8554. Min Act: -0.1700
Data Index: 1126831 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8554. Min Act: -0.1700
Data Index: 3308713 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8554. Min Act: -0.1700
Data Index: 2517808 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8554. Min Act: -0.1699
Data Index: 6501748 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8242. Min Act: -0.1700
Data Index: 743358 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8242. Min Act: -0.1700
Data Index: 2120970 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8242. Min Act: -0.1700
Data Index: 1657265 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8242. Min Act: -0.1700
Data Index: 4911353 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9492. Min Range: -4.9492
Max Act: 4.8242. Min Act: -0.1700
Data Index: 3449348 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19