Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5641 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.8944. Min Act: -0.1700
Data Index: 8150959 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.7694. Min Act: -0.1700
Data Index: 5562664 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.7381. Min Act: -0.1700
Data Index: 1896414 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.6756. Min Act: -0.1700
Data Index: 293195 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.6444. Min Act: -0.1700
Data Index: 2625505 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.6131. Min Act: -0.1700
Data Index: 4012662 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5819. Min Act: -0.1700
Data Index: 2276943 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5819. Min Act: -0.1700
Data Index: 106639 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5819. Min Act: -0.1700
Data Index: 4777200 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5506. Min Act: -0.1700
Data Index: 5360608 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5819. Min Act: -0.1700
Data Index: 5158948 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5506. Min Act: -0.1700
Data Index: 3760502 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5506. Min Act: -0.1700
Data Index: 2360934 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5506. Min Act: -0.1700
Data Index: 7778585 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.4881. Min Act: -0.1700
Data Index: 2085146 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.5194. Min Act: -0.1700
Data Index: 4642691 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.4569. Min Act: -0.1700
Data Index: 6494782 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.4881. Min Act: -0.1700
Data Index: 1138137 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.4881. Min Act: -0.1700
Data Index: 770171 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8944. Min Range: -5.8944
Max Act: 5.4881. Min Act: -0.1700
Data Index: 1877915 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19