Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1491 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.3388. Min Act: -0.1700
Data Index: 8481258 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.3075. Min Act: -0.1700
Data Index: 4547703 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.3075. Min Act: -0.1700
Data Index: 6181400 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.2138. Min Act: -0.1700
Data Index: 2003842 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.2138. Min Act: -0.1700
Data Index: 5225217 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1825. Min Act: -0.1700
Data Index: 7867606 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1512. Min Act: -0.1700
Data Index: 2146757 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1200. Min Act: -0.1700
Data Index: 6448429 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1512. Min Act: -0.1700
Data Index: 6728148 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1200. Min Act: -0.1700
Data Index: 2872112 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1512. Min Act: -0.1700
Data Index: 6387437 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1512. Min Act: -0.1700
Data Index: 7683350 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1200. Min Act: -0.1700
Data Index: 3027950 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.0887. Min Act: -0.1700
Data Index: 8402260 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1200. Min Act: -0.1700
Data Index: 3801891 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.0887. Min Act: -0.1700
Data Index: 3628845 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.0887. Min Act: -0.1700
Data Index: 5797294 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1200. Min Act: -0.1700
Data Index: 5489469 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1512. Min Act: -0.1700
Data Index: 5013709 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3388. Min Range: -4.3388
Max Act: 4.1200. Min Act: -0.1700
Data Index: 4066843 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19