Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 542 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.1062. Min Act: -0.1700
Data Index: 2431041 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.1374. Min Act: -0.1700
Data Index: 2797490 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0749. Min Act: -0.1700
Data Index: 547630 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0437. Min Act: -0.1700
Data Index: 4382771 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0437. Min Act: -0.1700
Data Index: 4963449 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0124. Min Act: -0.1700
Data Index: 2643562 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0124. Min Act: -0.1700
Data Index: 7253292 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0437. Min Act: -0.1700
Data Index: 5508241 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0124. Min Act: -0.1700
Data Index: 4886876 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9811. Min Act: -0.1700
Data Index: 7947026 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9811. Min Act: -0.1700
Data Index: 8180981 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9499. Min Act: -0.1700
Data Index: 2008504 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9499. Min Act: -0.1700
Data Index: 5427733 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9499. Min Act: -0.1700
Data Index: 148652 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9811. Min Act: -0.1700
Data Index: 5166984 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9186. Min Act: -0.1700
Data Index: 5001627 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9811. Min Act: -0.1700
Data Index: 3324662 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9499. Min Act: -0.1700
Data Index: 873469 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9499. Min Act: -0.1700
Data Index: 7796593 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9186. Min Act: -0.1700
Data Index: 2163579 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19