Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2313 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.6686. Min Act: -0.1700
Data Index: 3793239 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.6061. Min Act: -0.1700
Data Index: 6033831 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.5436. Min Act: -0.1700
Data Index: 5996598 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.5124. Min Act: -0.1700
Data Index: 6274798 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.5124. Min Act: -0.1700
Data Index: 4172966 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.4499. Min Act: -0.1700
Data Index: 823801 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.4186. Min Act: -0.1700
Data Index: 3750834 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.4186. Min Act: -0.1700
Data Index: 5824446 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3874. Min Act: -0.1700
Data Index: 5403854 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3561. Min Act: -0.1700
Data Index: 8150316 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3561. Min Act: -0.1700
Data Index: 8794171 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3561. Min Act: -0.1700
Data Index: 7809853 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3561. Min Act: -0.1700
Data Index: 6736541 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3249. Min Act: -0.1700
Data Index: 8693283 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3249. Min Act: -0.1700
Data Index: 2536104 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3249. Min Act: -0.1700
Data Index: 7463398 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3249. Min Act: -0.1700
Data Index: 8112449 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3249. Min Act: -0.1700
Data Index: 7565312 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.3561. Min Act: -0.1700
Data Index: 937395 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6686. Min Range: -5.6686
Max Act: 5.2936. Min Act: -0.1700
Data Index: 1988920 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19