Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1454 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.9434. Min Act: -0.1700
Data Index: 3891304 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5230556 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8965. Min Act: -0.1700
Data Index: 8359182 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8496. Min Act: -0.1700
Data Index: 6872700 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8653. Min Act: -0.1700
Data Index: 6807581 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8340. Min Act: -0.1700
Data Index: 4309208 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8809. Min Act: -0.1700
Data Index: 2505351 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8340. Min Act: -0.1700
Data Index: 4866880 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.8340. Min Act: -0.1700
Data Index: 3401865 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.7558. Min Act: -0.1700
Data Index: 8437058 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.7871. Min Act: -0.1700
Data Index: 7544406 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.6932. Min Act: -0.1700
Data Index: 977808 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.7402. Min Act: -0.1700
Data Index: 805640 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.6776. Min Act: -0.1700
Data Index: 8757568 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.5993. Min Act: -0.1700
Data Index: 1451078 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.7089. Min Act: -0.1700
Data Index: 3168337 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.6619. Min Act: -0.1700
Data Index: 4516196 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.6463. Min Act: -0.1700
Data Index: 238047 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.6150. Min Act: -0.1700
Data Index: 98748 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9434. Min Range: -3.9434
Max Act: 3.6932. Min Act: -0.1700
Data Index: 1540273 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19