Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1390 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.8672. Min Act: -0.1700
Data Index: 5794675 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.8359. Min Act: -0.1700
Data Index: 3275863 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7421. Min Act: -0.1700
Data Index: 73464 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7421. Min Act: -0.1700
Data Index: 87045 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7421. Min Act: -0.1700
Data Index: 8425572 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7421. Min Act: -0.1700
Data Index: 6653441 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7421. Min Act: -0.1700
Data Index: 2224160 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7421. Min Act: -0.1700
Data Index: 585772 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7108. Min Act: -0.1700
Data Index: 4856838 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7421. Min Act: -0.1700
Data Index: 6614591 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7108. Min Act: -0.1700
Data Index: 3033873 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.7108. Min Act: -0.1700
Data Index: 3266525 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6795. Min Act: -0.1700
Data Index: 5217709 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6795. Min Act: -0.1700
Data Index: 8642798 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6795. Min Act: -0.1700
Data Index: 2876512 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6795. Min Act: -0.1700
Data Index: 4755149 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6483. Min Act: -0.1700
Data Index: 7661687 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6170. Min Act: -0.1700
Data Index: 8014378 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6483. Min Act: -0.1700
Data Index: 2185848 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8672. Min Range: -3.8672
Max Act: 3.6483. Min Act: -0.1700
Data Index: 8163540 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19