Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4970 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7818. Min Range: -6.7818
Max Act: 6.7818. Min Act: -0.1700
Data Index: 5575823 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7818. Min Range: -6.7818
Max Act: 6.2506. Min Act: -0.1700
Data Index: 1697905 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7818. Min Range: -6.7818
Max Act: 6.1881. Min Act: -0.1700
Data Index: 5226505 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.9381. Min Act: -0.1700
Data Index: 5600787 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8756. Min Act: -0.1700
Data Index: 1146117 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8756. Min Act: -0.1700
Data Index: 2225727 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8756. Min Act: -0.1700
Data Index: 2348200 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8756. Min Act: -0.1700
Data Index: 6764644 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8756. Min Act: -0.1700
Data Index: 7073062 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1860919 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1809498 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8443. Min Act: -0.1700
Data Index: 8651945 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8443. Min Act: -0.1700
Data Index: 8709306 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8131. Min Act: -0.1700
Data Index: 946600 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8131. Min Act: -0.1700
Data Index: 3890094 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.7506. Min Act: -0.1700
Data Index: 8803722 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.7506. Min Act: -0.1700
Data Index: 7505446 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.8131. Min Act: -0.1700
Data Index: 2306989 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.7506. Min Act: -0.1700
Data Index: 4118950 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7818. Min Range: -6.7818
Max Act: 5.7506. Min Act: -0.1700
Data Index: 4826719 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19