Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2302. Min Range: -7.2302
Max Act: 7.2302. Min Act: -0.1700
Data Index: 7904233 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2302. Min Range: -7.2302
Max Act: 7.1365. Min Act: -0.1700
Data Index: 3069645 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.8865. Min Act: -0.1700
Data Index: 1630539 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.8240. Min Act: -0.1700
Data Index: 5966087 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.7927. Min Act: -0.1700
Data Index: 2061221 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.7615. Min Act: -0.1700
Data Index: 7154660 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.7302. Min Act: -0.1700
Data Index: 2685750 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.7302. Min Act: -0.1700
Data Index: 2015521 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6990. Min Act: -0.1700
Data Index: 4164256 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6990. Min Act: -0.1700
Data Index: 6270164 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6990. Min Act: -0.1700
Data Index: 7243553 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6677. Min Act: -0.1700
Data Index: 1742290 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6677. Min Act: -0.1700
Data Index: 8195955 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6677. Min Act: -0.1700
Data Index: 1939691 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6677. Min Act: -0.1700
Data Index: 6356869 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6365. Min Act: -0.1700
Data Index: 2465186 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6365. Min Act: -0.1700
Data Index: 3433762 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6052. Min Act: -0.1700
Data Index: 3250888 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.5740. Min Act: -0.1700
Data Index: 4159209 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2302. Min Range: -7.2302
Max Act: 6.6052. Min Act: -0.1700
Data Index: 2437333 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19