Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.2543. Min Act: -0.1700
Data Index: 8000924 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.1918. Min Act: -0.1700
Data Index: 8215429 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.1918. Min Act: -0.1700
Data Index: 7444837 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.1606. Min Act: -0.1700
Data Index: 6557603 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.1606. Min Act: -0.1700
Data Index: 5821287 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 8003730 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 7296073 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 6443054 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 2020560 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 3090892 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0668. Min Act: -0.1700
Data Index: 8418600 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0356. Min Act: -0.1700
Data Index: 1886861 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0356. Min Act: -0.1700
Data Index: 3597073 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0043. Min Act: -0.1700
Data Index: 5553712 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0043. Min Act: -0.1700
Data Index: 2026747 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2543. Min Range: -5.2543
Max Act: 5.0043. Min Act: -0.1700
Data Index: 3478176 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2543. Min Range: -5.2543
Max Act: 4.9731. Min Act: -0.1700
Data Index: 5700735 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2543. Min Range: -5.2543
Max Act: 4.9731. Min Act: -0.1700
Data Index: 6443388 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2543. Min Range: -5.2543
Max Act: 4.9731. Min Act: -0.1700
Data Index: 7237550 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2543. Min Range: -5.2543
Max Act: 4.9418. Min Act: -0.1700
Data Index: 751514 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19