Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5782 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2600. Min Range: -6.2600
Max Act: 6.2600. Min Act: -0.1700
Data Index: 1566290 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.9475. Min Act: -0.1694
Data Index: 3498935 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.9162. Min Act: -0.1700
Data Index: 286818 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.9162. Min Act: -0.1700
Data Index: 4190128 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.8537. Min Act: -0.1700
Data Index: 3571825 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.7912. Min Act: -0.1700
Data Index: 8389250 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.7600. Min Act: -0.1700
Data Index: 3631618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.7912. Min Act: -0.1700
Data Index: 5059867 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.7287. Min Act: -0.1700
Data Index: 8614773 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.7287. Min Act: -0.1700
Data Index: 3030944 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6975. Min Act: -0.1700
Data Index: 6626245 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.7287. Min Act: -0.1700
Data Index: 7703039 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6662. Min Act: -0.1699
Data Index: 2813370 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.7287. Min Act: -0.1700
Data Index: 594338 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6975. Min Act: -0.1700
Data Index: 8664324 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6662. Min Act: -0.1700
Data Index: 3297629 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1379342 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6662. Min Act: -0.1700
Data Index: 3105099 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6662. Min Act: -0.1700
Data Index: 5679775 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2600. Min Range: -6.2600
Max Act: 5.6662. Min Act: -0.1697
Data Index: 971284 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19