Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1865. Min Range: -8.1865
Max Act: 8.1865. Min Act: -0.1700
Data Index: 7346688 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1865. Min Range: -8.1865
Max Act: 8.1240. Min Act: -0.1700
Data Index: 2158574 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1865. Min Range: -8.1865
Max Act: 8.0928. Min Act: -0.1700
Data Index: 4237119 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1865. Min Range: -8.1865
Max Act: 8.0615. Min Act: -0.1700
Data Index: 1798115 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.9990. Min Act: -0.1700
Data Index: 7065916 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.9678. Min Act: -0.1700
Data Index: 8614855 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8740. Min Act: -0.1700
Data Index: 1383778 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8740. Min Act: -0.1700
Data Index: 1796577 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8740. Min Act: -0.1700
Data Index: 3347022 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8428. Min Act: -0.1700
Data Index: 1992588 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8428. Min Act: -0.1700
Data Index: 6882743 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8428. Min Act: -0.1700
Data Index: 7596008 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8115. Min Act: -0.1700
Data Index: 7442726 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8115. Min Act: -0.1699
Data Index: 7935929 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.7803. Min Act: -0.1700
Data Index: 3449109 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.8115. Min Act: -0.1700
Data Index: 6314478 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.7803. Min Act: -0.1700
Data Index: 1827330 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.7490. Min Act: -0.1700
Data Index: 1536092 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.6865. Min Act: -0.1700
Data Index: 2637163 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1865. Min Range: -8.1865
Max Act: 7.7178. Min Act: -0.1700
Data Index: 7596007 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19