Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4068 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1138. Min Range: -4.1138
Max Act: 4.1138. Min Act: -0.1700
Data Index: 5184499 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1138. Min Range: -4.1138
Max Act: 4.0826. Min Act: -0.1700
Data Index: 6893816 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.9575. Min Act: -0.1700
Data Index: 2301174 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.9575. Min Act: -0.1700
Data Index: 5291442 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.9263. Min Act: -0.1700
Data Index: 6560381 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.8950. Min Act: -0.1700
Data Index: 7877351 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.8325. Min Act: -0.1700
Data Index: 3126410 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.8168. Min Act: -0.1700
Data Index: 1176844 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.8325. Min Act: -0.1700
Data Index: 7748117 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.7543. Min Act: -0.1700
Data Index: 6340708 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.8012. Min Act: -0.1700
Data Index: 3053417 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.7230. Min Act: -0.1700
Data Index: 2537619 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.7074. Min Act: -0.1700
Data Index: 7522729 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.7074. Min Act: -0.1700
Data Index: 8600532 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.7230. Min Act: -0.1700
Data Index: 8450394 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.6917. Min Act: -0.1700
Data Index: 8065896 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.6917. Min Act: -0.1700
Data Index: 3103933 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.6604. Min Act: -0.1700
Data Index: 2963287 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.6761. Min Act: -0.1700
Data Index: 1683197 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1138. Min Range: -4.1138
Max Act: 3.6448. Min Act: -0.1700
Data Index: 187331 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19