Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4959 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.6678. Min Act: -0.1700
Data Index: 4063420 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.4490. Min Act: -0.1700
Data Index: 633295 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.3553. Min Act: -0.1700
Data Index: 1504527 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.3553. Min Act: -0.1700
Data Index: 5861053 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.3553. Min Act: -0.1700
Data Index: 8671124 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.3553. Min Act: -0.1700
Data Index: 6998639 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.3240. Min Act: -0.1700
Data Index: 3984664 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.3240. Min Act: -0.1700
Data Index: 1458394 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.2615. Min Act: -0.1700
Data Index: 7791034 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.2615. Min Act: -0.1700
Data Index: 112811 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.2615. Min Act: -0.1700
Data Index: 5435290 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.2303. Min Act: -0.1700
Data Index: 1369508 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.2303. Min Act: -0.1700
Data Index: 3811288 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.2303. Min Act: -0.1700
Data Index: 6743530 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.2303. Min Act: -0.1700
Data Index: 1981537 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.1990. Min Act: -0.1700
Data Index: 2025107 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.1990. Min Act: -0.1700
Data Index: 1013812 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.1990. Min Act: -0.1700
Data Index: 5858182 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.1677. Min Act: -0.1700
Data Index: 515063 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6678. Min Range: -4.6678
Max Act: 4.1677. Min Act: -0.1700
Data Index: 1691170 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19