Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 141 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2022. Min Range: -4.2022
Max Act: 4.2022. Min Act: -0.1700
Data Index: 3575619 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2022. Min Range: -4.2022
Max Act: 4.1397. Min Act: -0.1700
Data Index: 362160 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2022. Min Range: -4.2022
Max Act: 4.0771. Min Act: -0.1700
Data Index: 2535335 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2022. Min Range: -4.2022
Max Act: 4.0459. Min Act: -0.1700
Data Index: 6530277 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.9208. Min Act: -0.1700
Data Index: 3215825 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.9208. Min Act: -0.1700
Data Index: 3147083 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8896. Min Act: -0.1700
Data Index: 1667741 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8896. Min Act: -0.1700
Data Index: 8182854 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8896. Min Act: -0.1700
Data Index: 4099436 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8583. Min Act: -0.1700
Data Index: 5013046 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8583. Min Act: -0.1700
Data Index: 7016742 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8583. Min Act: -0.1700
Data Index: 8025890 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8583. Min Act: -0.1700
Data Index: 7344784 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8583. Min Act: -0.1700
Data Index: 2340837 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8583. Min Act: -0.1700
Data Index: 7108013 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8270. Min Act: -0.1700
Data Index: 7978267 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8270. Min Act: -0.1700
Data Index: 3206935 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.8270. Min Act: -0.1700
Data Index: 5242326 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7958. Min Act: -0.1700
Data Index: 4951841 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2022. Min Range: -4.2022
Max Act: 3.7645. Min Act: -0.1700
Data Index: 6016637 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19