Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1173 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.7452. Min Act: -0.1700
Data Index: 5411988 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.5574. Min Act: -0.1700
Data Index: 3927605 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.5261. Min Act: -0.1700
Data Index: 42510 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.5261. Min Act: -0.1700
Data Index: 1347826 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4791. Min Act: -0.1700
Data Index: 6348806 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4948. Min Act: -0.1700
Data Index: 6829908 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4791. Min Act: -0.1700
Data Index: 1716786 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4321. Min Act: -0.1700
Data Index: 6219014 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4478. Min Act: -0.1700
Data Index: 2798296 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4321. Min Act: -0.1700
Data Index: 8430033 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4321. Min Act: -0.1700
Data Index: 2304498 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4008. Min Act: -0.1700
Data Index: 739766 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4008. Min Act: -0.1700
Data Index: 576030 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4008. Min Act: -0.1700
Data Index: 3444324 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4008. Min Act: -0.1700
Data Index: 8105249 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4008. Min Act: -0.1700
Data Index: 7203325 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.3851. Min Act: -0.1700
Data Index: 5274912 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.3851. Min Act: -0.1700
Data Index: 2800877 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.4008. Min Act: -0.1700
Data Index: 6408852 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7452. Min Range: -3.7452
Max Act: 3.3851. Min Act: -0.1700
Data Index: 6888606 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19