Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 621 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.6881. Min Act: -0.1700
Data Index: 1544477 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.5944. Min Act: -0.1700
Data Index: 6080720 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.5006. Min Act: -0.1700
Data Index: 6349829 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.5006. Min Act: -0.1700
Data Index: 7723938 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.5006. Min Act: -0.1700
Data Index: 2979198 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.5006. Min Act: -0.1700
Data Index: 8182210 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.5006. Min Act: -0.1700
Data Index: 3841637 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4694. Min Act: -0.1700
Data Index: 2166419 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4694. Min Act: -0.1700
Data Index: 86632 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4694. Min Act: -0.1700
Data Index: 934132 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4694. Min Act: -0.1700
Data Index: 2821920 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4381. Min Act: -0.1700
Data Index: 8421138 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4694. Min Act: -0.1700
Data Index: 8776628 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4694. Min Act: -0.1700
Data Index: 648947 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4381. Min Act: -0.1700
Data Index: 4234695 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4381. Min Act: -0.1700
Data Index: 8001370 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4069. Min Act: -0.1700
Data Index: 132743 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4069. Min Act: -0.1700
Data Index: 228092 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.4069. Min Act: -0.1700
Data Index: 4529214 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6881. Min Range: -6.6881
Max Act: 6.3756. Min Act: -0.1700
Data Index: 1255330 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19