Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.7897. Min Act: -0.1700
Data Index: 2904372 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.7897. Min Act: -0.1700
Data Index: 6897066 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.6647. Min Act: -0.1700
Data Index: 3329225 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.6334. Min Act: -0.1700
Data Index: 2076383 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.6022. Min Act: -0.1700
Data Index: 3538533 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.6022. Min Act: -0.1700
Data Index: 3995227 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5984976 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5709. Min Act: -0.1700
Data Index: 5105692 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5397. Min Act: -0.1700
Data Index: 4739786 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5709. Min Act: -0.1700
Data Index: 2076382 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5709. Min Act: -0.1700
Data Index: 3953663 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5397. Min Act: -0.1700
Data Index: 6250110 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5397. Min Act: -0.1700
Data Index: 1018497 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5084. Min Act: -0.1700
Data Index: 4604644 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.5397. Min Act: -0.1700
Data Index: 5845105 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.4772. Min Act: -0.1700
Data Index: 2176828 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.4772. Min Act: -0.1700
Data Index: 25789 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.4147. Min Act: -0.1700
Data Index: 1311613 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.4459. Min Act: -0.1700
Data Index: 4131799 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7897. Min Range: -5.7897
Max Act: 5.4459. Min Act: -0.1700
Data Index: 1983282 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19