Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2287 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3167. Min Range: -8.3167
Max Act: 8.3167. Min Act: -0.1700
Data Index: 4635476 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3167. Min Range: -8.3167
Max Act: 8.2542. Min Act: -0.1700
Data Index: 2193197 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3167. Min Range: -8.3167
Max Act: 8.0042. Min Act: -0.1700
Data Index: 7463395 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.7542. Min Act: -0.1700
Data Index: 2643800 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.7542. Min Act: -0.1700
Data Index: 20771 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.6917. Min Act: -0.1700
Data Index: 836099 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.6292. Min Act: -0.1700
Data Index: 404395 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.5980. Min Act: -0.1700
Data Index: 858233 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.5980. Min Act: -0.1700
Data Index: 7330691 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.5980. Min Act: -0.1700
Data Index: 4526070 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.5355. Min Act: -0.1700
Data Index: 2118031 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.5667. Min Act: -0.1700
Data Index: 6518513 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.5042. Min Act: -0.1700
Data Index: 5313524 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.5042. Min Act: -0.1700
Data Index: 933477 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.4417. Min Act: -0.1700
Data Index: 5684932 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.4417. Min Act: -0.1700
Data Index: 478802 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.4105. Min Act: -0.1700
Data Index: 5292699 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.4105. Min Act: -0.1700
Data Index: 5663803 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.3792. Min Act: -0.1700
Data Index: 3914409 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3167. Min Range: -8.3167
Max Act: 7.3792. Min Act: -0.1700
Data Index: 6465053 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19