Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1182 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.3541. Min Act: -0.1700
Data Index: 1996671 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.2916. Min Act: -0.1700
Data Index: 4874608 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.2603. Min Act: -0.1700
Data Index: 8095790 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.1041. Min Act: -0.1700
Data Index: 8179288 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.1041. Min Act: -0.1700
Data Index: 4229581 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.1041. Min Act: -0.1700
Data Index: 8179295 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.0728. Min Act: -0.1700
Data Index: 700757 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.0416. Min Act: -0.1700
Data Index: 6960386 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.0416. Min Act: -0.1700
Data Index: 7531990 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3541. Min Range: -5.3541
Max Act: 5.0103. Min Act: -0.1700
Data Index: 422763 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.9791. Min Act: -0.1700
Data Index: 3523450 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.9791. Min Act: -0.1700
Data Index: 6169978 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8853. Min Act: -0.1700
Data Index: 5368843 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8853. Min Act: -0.1700
Data Index: 5368842 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8541. Min Act: -0.1700
Data Index: 106465 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8541. Min Act: -0.1700
Data Index: 7480098 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8541. Min Act: -0.1700
Data Index: 8600535 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8228. Min Act: -0.1700
Data Index: 4857786 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8228. Min Act: -0.1700
Data Index: 7583885 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3541. Min Range: -5.3541
Max Act: 4.8228. Min Act: -0.1700
Data Index: 1643282 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19