Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2225 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.2475. Min Act: -0.1700
Data Index: 5832732 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.2475. Min Act: -0.1700
Data Index: 2234697 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.2310. Min Act: -0.1700
Data Index: 5600262 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.2144. Min Act: -0.1700
Data Index: 4590978 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.2144. Min Act: -0.1700
Data Index: 4123717 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.2144. Min Act: -0.1700
Data Index: 5256313 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.2144. Min Act: -0.1700
Data Index: 8761896 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1812. Min Act: -0.1700
Data Index: 8409381 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1812. Min Act: -0.1700
Data Index: 6205948 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1978. Min Act: -0.1700
Data Index: 1286445 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1812. Min Act: -0.1700
Data Index: 5216370 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1812. Min Act: -0.1700
Data Index: 3445107 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1812. Min Act: -0.1700
Data Index: 5158051 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1812. Min Act: -0.1700
Data Index: 1769009 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1978. Min Act: -0.1700
Data Index: 7569941 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1646. Min Act: -0.1700
Data Index: 3146773 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1646. Min Act: -0.1700
Data Index: 6017642 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1646. Min Act: -0.1700
Data Index: 6721222 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1646. Min Act: -0.1700
Data Index: 4380805 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2475. Min Range: -2.2475
Max Act: 2.1646. Min Act: -0.1700
Data Index: 8093294 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19