Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1090 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0497. Min Range: -6.0497
Max Act: 6.0497. Min Act: -0.1700
Data Index: 3440540 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9872. Min Act: -0.1700
Data Index: 8198396 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9559. Min Act: -0.1700
Data Index: 8777615 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 7803506 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 6701025 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 8036551 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 5585944 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8934. Min Act: -0.1700
Data Index: 8688801 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 7585268 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8309. Min Act: -0.1700
Data Index: 7634372 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 4034963 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 3926021 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 7819876 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 869586 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8309. Min Act: -0.1700
Data Index: 607932 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8934. Min Act: -0.1700
Data Index: 7244976 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 7065440 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 4880716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 3497128 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 4787654 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19