Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0893. Min Range: -5.0893
Max Act: 5.0893. Min Act: -0.1700
Data Index: 6768397 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0893. Min Range: -5.0893
Max Act: 5.0581. Min Act: -0.1700
Data Index: 4529976 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9956. Min Act: -0.1700
Data Index: 4872584 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9643. Min Act: -0.1700
Data Index: 1793743 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9643. Min Act: -0.1700
Data Index: 3981612 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9643. Min Act: -0.1700
Data Index: 6475421 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9331. Min Act: -0.1700
Data Index: 2159209 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9331. Min Act: -0.1699
Data Index: 977943 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9018. Min Act: -0.1700
Data Index: 8259311 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.9018. Min Act: -0.1700
Data Index: 8132120 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8706. Min Act: -0.1700
Data Index: 3285727 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8706. Min Act: -0.1700
Data Index: 1612369 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8706. Min Act: -0.1700
Data Index: 3866344 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8081. Min Act: -0.1700
Data Index: 2422507 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8393. Min Act: -0.1700
Data Index: 762992 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8393. Min Act: -0.1700
Data Index: 2069699 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.7768. Min Act: -0.1700
Data Index: 6622730 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6195870 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.8081. Min Act: -0.1700
Data Index: 5278602 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0893. Min Range: -5.0893
Max Act: 4.7768. Min Act: -0.1700
Data Index: 313364 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19