Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2966. Min Act: -0.1700
Data Index: 2457974 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.3280. Min Act: -0.1700
Data Index: 7004622 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.3437. Min Act: -0.1700
Data Index: 4596908 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2966. Min Act: -0.1700
Data Index: 7002316 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2652. Min Act: -0.1700
Data Index: 1090592 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2652. Min Act: -0.1700
Data Index: 3892829 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2338. Min Act: -0.1700
Data Index: 5943500 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2181. Min Act: -0.1700
Data Index: 6042653 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2338. Min Act: -0.1700
Data Index: 8537051 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2024. Min Act: -0.1700
Data Index: 5825678 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.2181. Min Act: -0.1700
Data Index: 7798990 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1866. Min Act: -0.1700
Data Index: 5840897 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1866. Min Act: -0.1700
Data Index: 3719759 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1866. Min Act: -0.1700
Data Index: 1494593 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1552. Min Act: -0.1700
Data Index: 3185456 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1237. Min Act: -0.1700
Data Index: 8673958 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1866. Min Act: -0.1700
Data Index: 5514497 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1552. Min Act: -0.1700
Data Index: 7145546 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1237. Min Act: -0.1700
Data Index: 3408628 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3437. Min Range: -3.3437
Max Act: 3.1394. Min Act: -0.1700
Data Index: 5216304 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19