Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.4490. Min Act: -0.1700
Data Index: 347072 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.3553. Min Act: -0.1700
Data Index: 8281731 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.2302. Min Act: -0.1700
Data Index: 2414890 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1990. Min Act: -0.1700
Data Index: 4000856 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1677. Min Act: -0.1700
Data Index: 2155666 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1365. Min Act: -0.1700
Data Index: 26835 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1677. Min Act: -0.1700
Data Index: 3584585 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1365. Min Act: -0.1700
Data Index: 7282543 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.0740. Min Act: -0.1700
Data Index: 7695075 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1677. Min Act: -0.1700
Data Index: 2236738 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1052. Min Act: -0.1700
Data Index: 2501383 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1052. Min Act: -0.1700
Data Index: 5866367 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1052. Min Act: -0.1700
Data Index: 8486698 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1365. Min Act: -0.1700
Data Index: 1071631 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1365. Min Act: -0.1700
Data Index: 373943 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1052. Min Act: -0.1700
Data Index: 999847 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.1052. Min Act: -0.1700
Data Index: 4135647 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.0740. Min Act: -0.1700
Data Index: 1113713 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.0427. Min Act: -0.1700
Data Index: 1212607 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4490. Min Range: -4.4490
Max Act: 4.0427. Min Act: -0.1700
Data Index: 3610713 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19