Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.4948. Min Act: -0.1700
Data Index: 7076561 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.4323. Min Act: -0.1700
Data Index: 7278034 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.4323. Min Act: -0.1700
Data Index: 4712831 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.4323. Min Act: -0.1700
Data Index: 1806406 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.4323. Min Act: -0.1700
Data Index: 687442 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.4323. Min Act: -0.1700
Data Index: 4288563 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.3698. Min Act: -0.1700
Data Index: 4592081 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.3073. Min Act: -0.1700
Data Index: 3681964 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.3073. Min Act: -0.1700
Data Index: 4592082 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.3073. Min Act: -0.1700
Data Index: 274347 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.2448. Min Act: -0.1700
Data Index: 1078215 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.2448. Min Act: -0.1700
Data Index: 4288541 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.2448. Min Act: -0.1700
Data Index: 559482 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.2448. Min Act: -0.1700
Data Index: 4288562 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.2448. Min Act: -0.1700
Data Index: 8640549 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.2448. Min Act: -0.1700
Data Index: 7765699 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.1823. Min Act: -0.1700
Data Index: 4168524 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.1823. Min Act: -0.1700
Data Index: 1271556 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.1823. Min Act: -0.1700
Data Index: 3882833 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4948. Min Range: -7.4948
Max Act: 7.1823. Min Act: -0.1700
Data Index: 4791217 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19