Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5358 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.6902. Min Act: -0.1700
Data Index: 8174950 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.6590. Min Act: -0.1700
Data Index: 4844588 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.6277. Min Act: -0.1700
Data Index: 5347900 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.5340. Min Act: -0.1700
Data Index: 1299835 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.5027. Min Act: -0.1700
Data Index: 3385883 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4715. Min Act: -0.1700
Data Index: 1543556 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6928161 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4715. Min Act: -0.1700
Data Index: 7250718 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4402. Min Act: -0.1700
Data Index: 902881 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4715. Min Act: -0.1700
Data Index: 4927255 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4402. Min Act: -0.1700
Data Index: 1355882 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4402. Min Act: -0.1700
Data Index: 5292823 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4090. Min Act: -0.1700
Data Index: 4226104 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4402. Min Act: -0.1700
Data Index: 4291220 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3880702 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3021326 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2921247 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.3777. Min Act: -0.1700
Data Index: 8365583 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.3777. Min Act: -0.1700
Data Index: 3782051 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6902. Min Range: -5.6902
Max Act: 5.3465. Min Act: -0.1700
Data Index: 4541796 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19