Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2920. Min Range: -5.2920
Max Act: 5.2920. Min Act: -0.1700
Data Index: 1488926 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2920. Min Range: -5.2920
Max Act: 5.1982. Min Act: -0.1700
Data Index: 2957643 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2920. Min Range: -5.2920
Max Act: 5.0732. Min Act: -0.1700
Data Index: 3951556 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.9482. Min Act: -0.1700
Data Index: 7712893 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.9482. Min Act: -0.1700
Data Index: 4778821 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.9170. Min Act: -0.1700
Data Index: 4372754 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8857. Min Act: -0.1700
Data Index: 7850847 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.9170. Min Act: -0.1700
Data Index: 6181798 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8545. Min Act: -0.1700
Data Index: 6919252 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8545. Min Act: -0.1700
Data Index: 2019666 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8545. Min Act: -0.1700
Data Index: 1296640 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8545. Min Act: -0.1700
Data Index: 6204792 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8545. Min Act: -0.1700
Data Index: 1040846 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8545. Min Act: -0.1700
Data Index: 6244949 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8545. Min Act: -0.1700
Data Index: 7471981 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.8232. Min Act: -0.1700
Data Index: 7796459 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.7607. Min Act: -0.1700
Data Index: 5859767 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.7607. Min Act: -0.1700
Data Index: 2618250 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.7607. Min Act: -0.1700
Data Index: 8468964 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2920. Min Range: -5.2920
Max Act: 4.7295. Min Act: -0.1700
Data Index: 349386 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19