Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4060 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.3305. Min Act: -0.1700
Data Index: 1167224 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.2680. Min Act: -0.1700
Data Index: 1600723 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.2993. Min Act: -0.1700
Data Index: 5786743 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.2680. Min Act: -0.1700
Data Index: 6860012 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.2055. Min Act: -0.1700
Data Index: 1501580 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.2055. Min Act: -0.1700
Data Index: 7786615 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1743. Min Act: -0.1700
Data Index: 3832349 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1743. Min Act: -0.1700
Data Index: 6860009 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1430. Min Act: -0.1700
Data Index: 7477094 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1118. Min Act: -0.1700
Data Index: 1501584 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1118. Min Act: -0.1700
Data Index: 2526766 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1430. Min Act: -0.1700
Data Index: 8169056 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1118. Min Act: -0.1700
Data Index: 2757105 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1118. Min Act: -0.1700
Data Index: 8489921 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1430. Min Act: -0.1700
Data Index: 504739 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.1118. Min Act: -0.1700
Data Index: 6655159 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0805. Min Act: -0.1700
Data Index: 7890198 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0805. Min Act: -0.1700
Data Index: 4171268 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0493. Min Act: -0.1700
Data Index: 5347255 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3305. Min Range: -5.3305
Max Act: 5.0493. Min Act: -0.1700
Data Index: 1235487 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19