Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2513 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.9975. Min Act: -0.1700
Data Index: 7571091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.9037. Min Act: -0.1700
Data Index: 991164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.9037. Min Act: -0.1700
Data Index: 2203370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.9037. Min Act: -0.1700
Data Index: 1952302 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.8724. Min Act: -0.1700
Data Index: 792942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.8412. Min Act: -0.1700
Data Index: 1781755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.8099. Min Act: -0.1700
Data Index: 8821426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7786. Min Act: -0.1700
Data Index: 2854860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.8099. Min Act: -0.1700
Data Index: 8011755 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7473. Min Act: -0.1700
Data Index: 8586601 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7473. Min Act: -0.1700
Data Index: 2739499 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7473. Min Act: -0.1699
Data Index: 8586598 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7473. Min Act: -0.1700
Data Index: 8586599 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7473. Min Act: -0.1700
Data Index: 1379269 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7473. Min Act: -0.1700
Data Index: 4063137 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.6848. Min Act: -0.1700
Data Index: 382122 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7160. Min Act: -0.1700
Data Index: 2089363 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7160. Min Act: -0.1700
Data Index: 2184434 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7160. Min Act: -0.1700
Data Index: 2614178 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9975. Min Range: -3.9975
Max Act: 3.7160. Min Act: -0.1700
Data Index: 461458 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19