Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3381. Min Range: -7.3381
Max Act: 7.3381. Min Act: -0.1700
Data Index: 3183994 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3381. Min Range: -7.3381
Max Act: 7.2756. Min Act: -0.1700
Data Index: 3959923 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3381. Min Range: -7.3381
Max Act: 7.1818. Min Act: -0.1700
Data Index: 2567160 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3381. Min Range: -7.3381
Max Act: 7.1506. Min Act: -0.1700
Data Index: 4277485 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3381. Min Range: -7.3381
Max Act: 7.0881. Min Act: -0.1700
Data Index: 2290664 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3381. Min Range: -7.3381
Max Act: 7.0881. Min Act: -0.1700
Data Index: 7138580 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.9006. Min Act: -0.1700
Data Index: 8213418 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.9006. Min Act: -0.1700
Data Index: 8623667 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.8381. Min Act: -0.1700
Data Index: 4402040 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.7756. Min Act: -0.1700
Data Index: 1630556 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.8068. Min Act: -0.1700
Data Index: 440447 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.7443. Min Act: -0.1700
Data Index: 2977640 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.7443. Min Act: -0.1700
Data Index: 1627161 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.7443. Min Act: -0.1700
Data Index: 2060785 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.7131. Min Act: -0.1700
Data Index: 6608571 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.6818. Min Act: -0.1700
Data Index: 1978849 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.6818. Min Act: -0.1700
Data Index: 2142620 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.6818. Min Act: -0.1700
Data Index: 5943442 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.6193. Min Act: -0.1700
Data Index: 1722603 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3381. Min Range: -7.3381
Max Act: 6.6193. Min Act: -0.1700
Data Index: 7815646 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19