Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4281 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0105. Min Range: -4.0105
Max Act: 4.0105. Min Act: -0.1700
Data Index: 4717049 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.9479. Min Act: -0.1668
Data Index: 5513619 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7916. Min Act: -0.1613
Data Index: 6109126 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7916. Min Act: -0.1642
Data Index: 1456663 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7603. Min Act: -0.1700
Data Index: 3809751 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7916. Min Act: -0.1640
Data Index: 1860554 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7916. Min Act: -0.1674
Data Index: 252879 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7916. Min Act: -0.1616
Data Index: 579671 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7916. Min Act: -0.1691
Data Index: 2561154 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7603. Min Act: -0.1694
Data Index: 3224613 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7290. Min Act: -0.1637
Data Index: 311069 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7290. Min Act: -0.1450
Data Index: 1801379 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7290. Min Act: -0.1680
Data Index: 506790 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7290. Min Act: -0.1699
Data Index: 8605110 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7290. Min Act: -0.1572
Data Index: 5806028 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.7290. Min Act: -0.1671
Data Index: 4618820 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.6978. Min Act: -0.1697
Data Index: 4157169 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.6978. Min Act: -0.1700
Data Index: 2202045 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.6665. Min Act: -0.1699
Data Index: 8482084 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0105. Min Range: -4.0105
Max Act: 3.6665. Min Act: -0.1700
Data Index: 7147073 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19