Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0006. Min Range: -7.0006
Max Act: 7.0006. Min Act: -0.1700
Data Index: 3216691 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.9693. Min Act: -0.1700
Data Index: 4167249 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.8756. Min Act: -0.1700
Data Index: 2041341 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.8131. Min Act: -0.1700
Data Index: 7178895 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.7506. Min Act: -0.1700
Data Index: 4859533 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.6256. Min Act: -0.1700
Data Index: 7785781 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.5631. Min Act: -0.1700
Data Index: 3844847 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.5006. Min Act: -0.1700
Data Index: 5043554 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.5006. Min Act: -0.1700
Data Index: 6663899 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.5006. Min Act: -0.1700
Data Index: 967228 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4693. Min Act: -0.1700
Data Index: 7923398 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4693. Min Act: -0.1700
Data Index: 7771944 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4381. Min Act: -0.1700
Data Index: 6417812 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4381. Min Act: -0.1700
Data Index: 1732746 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4068. Min Act: -0.1700
Data Index: 3154254 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4068. Min Act: -0.1700
Data Index: 6228375 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4068. Min Act: -0.1700
Data Index: 1366433 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.4068. Min Act: -0.1700
Data Index: 6524244 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.3756. Min Act: -0.1700
Data Index: 2566584 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0006. Min Range: -7.0006
Max Act: 6.3756. Min Act: -0.1700
Data Index: 4390133 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19