Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4760 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0675. Min Range: -7.0675
Max Act: 7.0675. Min Act: -0.1700
Data Index: 7469604 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.9737. Min Act: -0.1700
Data Index: 8095745 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.8487. Min Act: -0.1700
Data Index: 5188266 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.6925. Min Act: -0.1700
Data Index: 4441319 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.6300. Min Act: -0.1700
Data Index: 1463042 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.5675. Min Act: -0.1700
Data Index: 6865830 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.5362. Min Act: -0.1700
Data Index: 1193098 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.4737. Min Act: -0.1700
Data Index: 28398 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.5050. Min Act: -0.1700
Data Index: 5298944 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.4425. Min Act: -0.1700
Data Index: 2959381 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.4737. Min Act: -0.1700
Data Index: 1279860 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.4425. Min Act: -0.1700
Data Index: 793677 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.3487. Min Act: -0.1700
Data Index: 1327548 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.3487. Min Act: -0.1700
Data Index: 7218446 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.3487. Min Act: -0.1700
Data Index: 6307533 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.3175. Min Act: -0.1700
Data Index: 5930767 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.3175. Min Act: -0.1700
Data Index: 1040986 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.2550. Min Act: -0.1700
Data Index: 6833179 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.2550. Min Act: -0.1700
Data Index: 5667090 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0675. Min Range: -7.0675
Max Act: 6.2237. Min Act: -0.1700
Data Index: 4166319 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19