Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.3774. Min Act: -0.1700
Data Index: 5081562 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.3774. Min Act: -0.1700
Data Index: 6301670 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.1899. Min Act: -0.1700
Data Index: 2723981 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.0962. Min Act: -0.1700
Data Index: 5150273 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.0649. Min Act: -0.1700
Data Index: 8679402 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.0649. Min Act: -0.1700
Data Index: 1282716 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.0337. Min Act: -0.1700
Data Index: 6894633 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.0649. Min Act: -0.1700
Data Index: 3338988 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.0337. Min Act: -0.1700
Data Index: 7156153 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3774. Min Range: -6.3774
Max Act: 6.0024. Min Act: -0.1700
Data Index: 5333118 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9712. Min Act: -0.1700
Data Index: 5862242 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9712. Min Act: -0.1700
Data Index: 5318908 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9399. Min Act: -0.1700
Data Index: 2474162 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9399. Min Act: -0.1700
Data Index: 8711021 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9399. Min Act: -0.1700
Data Index: 4275198 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9712. Min Act: -0.1700
Data Index: 4529269 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9399. Min Act: -0.1700
Data Index: 2684899 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9087. Min Act: -0.1700
Data Index: 6287326 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9087. Min Act: -0.1700
Data Index: 2491498 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3774. Min Range: -6.3774
Max Act: 5.9087. Min Act: -0.1700
Data Index: 1004653 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19