Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5579 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4163. Min Range: -8.4163
Max Act: 8.4163. Min Act: -0.1700
Data Index: 8120863 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.9788. Min Act: -0.1700
Data Index: 6790550 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.8538. Min Act: -0.1700
Data Index: 2843866 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.6975. Min Act: -0.1700
Data Index: 4618975 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.6663. Min Act: -0.1700
Data Index: 6823644 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.6350. Min Act: -0.1700
Data Index: 4097089 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.6038. Min Act: -0.1700
Data Index: 6001824 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.6038. Min Act: -0.1700
Data Index: 8407605 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.5413. Min Act: -0.1700
Data Index: 1292370 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.5100. Min Act: -0.1700
Data Index: 5026566 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.5100. Min Act: -0.1700
Data Index: 3618414 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.5100. Min Act: -0.1700
Data Index: 6903122 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.4788. Min Act: -0.1700
Data Index: 7329624 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.4475. Min Act: -0.1700
Data Index: 2014180 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.4788. Min Act: -0.1700
Data Index: 3989885 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.4475. Min Act: -0.1700
Data Index: 7791860 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.4475. Min Act: -0.1700
Data Index: 3816597 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.4475. Min Act: -0.1700
Data Index: 5438774 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.4163. Min Act: -0.1700
Data Index: 7642284 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4163. Min Range: -8.4163
Max Act: 7.3850. Min Act: -0.1700
Data Index: 3632611 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19