Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2453 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.7928. Min Act: -0.1700
Data Index: 941189 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.5428. Min Act: -0.1700
Data Index: 4642388 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.4491. Min Act: -0.1700
Data Index: 8587719 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.3866. Min Act: -0.1700
Data Index: 8059359 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.3553. Min Act: -0.1700
Data Index: 5248415 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2928. Min Act: -0.1700
Data Index: 2899690 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2616. Min Act: -0.1700
Data Index: 813590 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2928. Min Act: -0.1700
Data Index: 615315 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2616. Min Act: -0.1700
Data Index: 729100 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2303. Min Act: -0.1700
Data Index: 7315795 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2303. Min Act: -0.1700
Data Index: 8769635 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2616. Min Act: -0.1700
Data Index: 7584216 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2303. Min Act: -0.1700
Data Index: 2720265 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2303. Min Act: -0.1700
Data Index: 5916984 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2303. Min Act: -0.1700
Data Index: 8493234 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.2303. Min Act: -0.1700
Data Index: 7802566 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.1991. Min Act: -0.1700
Data Index: 6328759 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.1991. Min Act: -0.1700
Data Index: 2175381 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.1991. Min Act: -0.1700
Data Index: 963655 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7928. Min Range: -6.7928
Max Act: 6.1678. Min Act: -0.1700
Data Index: 7277542 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19