Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4237 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.7633. Min Act: -0.1700
Data Index: 7616853 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.7633. Min Act: -0.1700
Data Index: 4999506 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.6383. Min Act: -0.1700
Data Index: 2531075 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.5133. Min Act: -0.1700
Data Index: 1098327 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.4508. Min Act: -0.1700
Data Index: 52045 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.3258. Min Act: -0.1700
Data Index: 4294567 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.3258. Min Act: -0.1700
Data Index: 103015 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.2633. Min Act: -0.1700
Data Index: 2214704 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.2008. Min Act: -0.1700
Data Index: 339846 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.2008. Min Act: -0.1700
Data Index: 7375122 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.1696. Min Act: -0.1700
Data Index: 2080349 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.1696. Min Act: -0.1700
Data Index: 1469532 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.2008. Min Act: -0.1700
Data Index: 3039886 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.1071. Min Act: -0.1700
Data Index: 620457 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.0758. Min Act: -0.1700
Data Index: 4847098 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7633. Min Range: -8.7633
Max Act: 8.0133. Min Act: -0.1700
Data Index: 7262307 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7633. Min Range: -8.7633
Max Act: 7.9821. Min Act: -0.1700
Data Index: 1520390 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7633. Min Range: -8.7633
Max Act: 7.9508. Min Act: -0.1700
Data Index: 3633274 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7633. Min Range: -8.7633
Max Act: 7.9508. Min Act: -0.1700
Data Index: 3460469 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7633. Min Range: -8.7633
Max Act: 7.9508. Min Act: -0.1700
Data Index: 2467148 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19