Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1504 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2111. Min Range: -3.2111
Max Act: 3.2111. Min Act: -0.1700
Data Index: 8542580 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2111. Min Range: -3.2111
Max Act: 3.1639. Min Act: -0.1700
Data Index: 2796871 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2111. Min Range: -3.2111
Max Act: 3.0536. Min Act: -0.1700
Data Index: 6451157 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2111. Min Range: -3.2111
Max Act: 3.0378. Min Act: -0.1700
Data Index: 1135963 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2111. Min Range: -3.2111
Max Act: 3.0062. Min Act: -0.1700
Data Index: 8542575 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.9904. Min Act: -0.1700
Data Index: 2213222 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.9904. Min Act: -0.1700
Data Index: 8309221 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.9746. Min Act: -0.1700
Data Index: 6736674 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.9904. Min Act: -0.1700
Data Index: 8306721 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1224624 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8954. Min Act: -0.1700
Data Index: 4921554 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 1204771 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 4307306 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 8524752 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 5223053 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 7963883 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 3898667 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 7939415 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 6771647 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2111. Min Range: -3.2111
Max Act: 2.8795. Min Act: -0.1700
Data Index: 5212695 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19