Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.5721. Min Act: -0.1700
Data Index: 7630501 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.5409. Min Act: -0.1700
Data Index: 7630499 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.4159. Min Act: -0.1700
Data Index: 3005320 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.3846. Min Act: -0.1700
Data Index: 3222842 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.3846. Min Act: -0.1700
Data Index: 8475607 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.4471. Min Act: -0.1700
Data Index: 3904884 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.3221. Min Act: -0.1700
Data Index: 2644530 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.3534. Min Act: -0.1700
Data Index: 7377093 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.3534. Min Act: -0.1700
Data Index: 6288125 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.3534. Min Act: -0.1700
Data Index: 1018937 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.2284. Min Act: -0.1700
Data Index: 216027 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.3846. Min Act: -0.1700
Data Index: 6253557 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.1346. Min Act: -0.1700
Data Index: 270315 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.2284. Min Act: -0.1700
Data Index: 459526 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.2284. Min Act: -0.1700
Data Index: 204141 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.1659. Min Act: -0.1700
Data Index: 2184422 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.1971. Min Act: -0.1700
Data Index: 5771603 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.1971. Min Act: -0.1700
Data Index: 8244804 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.2596. Min Act: -0.1700
Data Index: 561203 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5721. Min Range: -7.5721
Max Act: 7.1971. Min Act: -0.1700
Data Index: 2350720 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19