Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.7304. Min Act: -0.1700
Data Index: 6510524 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.6991. Min Act: -0.1700
Data Index: 8003475 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5896. Min Act: -0.1700
Data Index: 294180 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5896. Min Act: -0.1700
Data Index: 1236737 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5739. Min Act: -0.1700
Data Index: 7812840 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5426. Min Act: -0.1700
Data Index: 3069273 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5583. Min Act: -0.1700
Data Index: 4437611 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5583. Min Act: -0.1700
Data Index: 7447576 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5426. Min Act: -0.1700
Data Index: 6303220 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5426. Min Act: -0.1700
Data Index: 8675532 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5270. Min Act: -0.1700
Data Index: 8637371 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5113. Min Act: -0.1700
Data Index: 3156250 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.4957. Min Act: -0.1700
Data Index: 5185325 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5113. Min Act: -0.1700
Data Index: 2836435 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.5113. Min Act: -0.1700
Data Index: 8698240 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.4643. Min Act: -0.1700
Data Index: 1839744 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.4800. Min Act: -0.1700
Data Index: 968541 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.4800. Min Act: -0.1700
Data Index: 3524305 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.4800. Min Act: -0.1700
Data Index: 1635998 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7304. Min Range: -3.7304
Max Act: 3.4643. Min Act: -0.1700
Data Index: 7484498 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19