Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1054. Min Range: -3.1054
Max Act: 3.1054. Min Act: -0.1700
Data Index: 8773657 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1054. Min Range: -3.1054
Max Act: 3.0897. Min Act: -0.1700
Data Index: 8330026 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1054. Min Range: -3.1054
Max Act: 3.0897. Min Act: -0.1700
Data Index: 6883100 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1054. Min Range: -3.1054
Max Act: 3.0739. Min Act: -0.1700
Data Index: 1138646 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1054. Min Range: -3.1054
Max Act: 3.0581. Min Act: -0.1700
Data Index: 4157905 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9950. Min Act: -0.1700
Data Index: 8241817 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9950. Min Act: -0.1700
Data Index: 8330021 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9950. Min Act: -0.1700
Data Index: 8330022 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9791. Min Act: -0.1700
Data Index: 5090911 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9791. Min Act: -0.1699
Data Index: 6883082 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9475. Min Act: -0.1700
Data Index: 8773659 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9475. Min Act: -0.1700
Data Index: 5240169 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9475. Min Act: -0.1700
Data Index: 6883074 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9317. Min Act: -0.1700
Data Index: 6450451 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9158. Min Act: -0.1700
Data Index: 1395088 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9158. Min Act: -0.1700
Data Index: 8197163 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9158. Min Act: -0.1700
Data Index: 5240168 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9000. Min Act: -0.1700
Data Index: 8271495 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.9000. Min Act: -0.1700
Data Index: 6883088 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1054. Min Range: -3.1054
Max Act: 2.8841. Min Act: -0.1700
Data Index: 6883071 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19