Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4657. Min Range: -7.4657
Max Act: 7.4657. Min Act: -0.1700
Data Index: 1350024 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.7782. Min Act: -0.1700
Data Index: 4643265 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.7470. Min Act: -0.1700
Data Index: 8519163 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.6845. Min Act: -0.1700
Data Index: 7415711 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.5907. Min Act: -0.1700
Data Index: 1759161 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.5595. Min Act: -0.1700
Data Index: 5611797 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.5907. Min Act: -0.1700
Data Index: 3867199 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.5595. Min Act: -0.1700
Data Index: 2999679 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.5907. Min Act: -0.1700
Data Index: 5493686 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.5282. Min Act: -0.1700
Data Index: 6878738 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.4970. Min Act: -0.1700
Data Index: 2762882 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.4970. Min Act: -0.1700
Data Index: 5204998 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.4970. Min Act: -0.1700
Data Index: 6324142 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.4657. Min Act: -0.1700
Data Index: 834455 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.4345. Min Act: -0.1700
Data Index: 7811358 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.4345. Min Act: -0.1700
Data Index: 3729298 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1086616 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.3720. Min Act: -0.1700
Data Index: 7781888 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.3720. Min Act: -0.1700
Data Index: 4601747 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4657. Min Range: -7.4657
Max Act: 6.3720. Min Act: -0.1700
Data Index: 3443879 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19