Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.5730. Min Act: -0.1700
Data Index: 7378361 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.3230. Min Act: -0.1700
Data Index: 8578833 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.1980. Min Act: -0.1700
Data Index: 4107315 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.1667. Min Act: -0.1700
Data Index: 8187106 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.1355. Min Act: -0.1700
Data Index: 779610 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.1042. Min Act: -0.1700
Data Index: 4202448 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.1042. Min Act: -0.1700
Data Index: 6712209 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5730. Min Range: -7.5730
Max Act: 7.0417. Min Act: -0.1700
Data Index: 3795257 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.9792. Min Act: -0.1700
Data Index: 8182700 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.9792. Min Act: -0.1700
Data Index: 65208 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.9792. Min Act: -0.1700
Data Index: 6685878 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.9167. Min Act: -0.1700
Data Index: 8618800 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.9167. Min Act: -0.1700
Data Index: 7956126 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.8855. Min Act: -0.1700
Data Index: 7417830 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.8855. Min Act: -0.1700
Data Index: 7174744 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.8542. Min Act: -0.1700
Data Index: 4887452 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.8542. Min Act: -0.1700
Data Index: 4636087 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.8230. Min Act: -0.1700
Data Index: 6270899 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.8230. Min Act: -0.1700
Data Index: 7468394 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5730. Min Range: -7.5730
Max Act: 6.8230. Min Act: -0.1700
Data Index: 5287080 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19