Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 291 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7353. Min Act: -0.1700
Data Index: 2439458 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7666. Min Act: -0.1699
Data Index: 3629084 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7666. Min Act: -0.1700
Data Index: 7715243 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7353. Min Act: -0.1700
Data Index: 1485023 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7666. Min Act: -0.1700
Data Index: 5397381 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7041. Min Act: -0.1697
Data Index: 2427513 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.7041. Min Act: -0.1700
Data Index: 5177037 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6416. Min Act: -0.1700
Data Index: 2799596 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6728. Min Act: -0.1700
Data Index: 6162192 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1697
Data Index: 1583746 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6416. Min Act: -0.1700
Data Index: 7523423 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1700
Data Index: 588084 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1700
Data Index: 2445404 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1700
Data Index: 2445551 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6416. Min Act: -0.1700
Data Index: 7955619 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1700
Data Index: 6325606 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1700
Data Index: 4312114 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1700
Data Index: 1349667 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.5791. Min Act: -0.1700
Data Index: 635707 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7666. Min Range: -5.7666
Max Act: 5.6103. Min Act: -0.1692
Data Index: 6183551 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19