Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5196 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.1646. Min Act: -0.1700
Data Index: 4553774 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.1334. Min Act: -0.1700
Data Index: 5174457 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.1334. Min Act: -0.1700
Data Index: 1564218 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.1021. Min Act: -0.1700
Data Index: 7845803 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.0396. Min Act: -0.1700
Data Index: 915270 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.0396. Min Act: -0.1700
Data Index: 4293975 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.0396. Min Act: -0.1700
Data Index: 2150295 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.0396. Min Act: -0.1700
Data Index: 1736271 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.0084. Min Act: -0.1700
Data Index: 2558333 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.0084. Min Act: -0.1700
Data Index: 4200970 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1646. Min Range: -5.1646
Max Act: 5.0084. Min Act: -0.1700
Data Index: 8173321 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9771. Min Act: -0.1700
Data Index: 3682464 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9771. Min Act: -0.1700
Data Index: 7739668 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9771. Min Act: -0.1700
Data Index: 4582795 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9771. Min Act: -0.1700
Data Index: 6668782 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9459. Min Act: -0.1700
Data Index: 4887812 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9771. Min Act: -0.1700
Data Index: 1776602 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9771. Min Act: -0.1700
Data Index: 4956897 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9771. Min Act: -0.1700
Data Index: 3820122 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1646. Min Range: -5.1646
Max Act: 4.9459. Min Act: -0.1700
Data Index: 1488380 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19