Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.9490. Min Act: -0.1700
Data Index: 8643062 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.9177. Min Act: -0.1700
Data Index: 2688508 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.8552. Min Act: -0.1700
Data Index: 1343234 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.8240. Min Act: -0.1700
Data Index: 3735987 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.8240. Min Act: -0.1700
Data Index: 5752303 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.8240. Min Act: -0.1700
Data Index: 4712494 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.8552. Min Act: -0.1700
Data Index: 8554497 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.7615. Min Act: -0.1700
Data Index: 7647692 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.7615. Min Act: -0.1700
Data Index: 6588058 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.7615. Min Act: -0.1700
Data Index: 4661738 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1816035 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6990. Min Act: -0.1700
Data Index: 5490359 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6990. Min Act: -0.1700
Data Index: 2706252 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6990. Min Act: -0.1700
Data Index: 4288438 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6990. Min Act: -0.1700
Data Index: 6108993 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6990. Min Act: -0.1700
Data Index: 1513406 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6677. Min Act: -0.1698
Data Index: 148222 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6677. Min Act: -0.1700
Data Index: 3188528 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6365. Min Act: -0.1700
Data Index: 1772168 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9490. Min Range: -5.9490
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2520612 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19