Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6116 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2225. Min Range: -7.2225
Max Act: 7.2225. Min Act: -0.1700
Data Index: 8609822 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2225. Min Range: -7.2225
Max Act: 7.1600. Min Act: -0.1700
Data Index: 7348109 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2225. Min Range: -7.2225
Max Act: 7.1287. Min Act: -0.1700
Data Index: 6928560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2225. Min Range: -7.2225
Max Act: 7.0662. Min Act: -0.1700
Data Index: 7039092 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2225. Min Range: -7.2225
Max Act: 7.0037. Min Act: -0.1700
Data Index: 5975629 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9412. Min Act: -0.1700
Data Index: 3763606 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9725. Min Act: -0.1700
Data Index: 7328735 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 3890685 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9412. Min Act: -0.1700
Data Index: 7195832 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 426320 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 1220319 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 1306910 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 1156129 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 3095538 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.8162. Min Act: -0.1700
Data Index: 6555095 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 1624583 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.8475. Min Act: -0.1700
Data Index: 1870120 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.7537. Min Act: -0.1700
Data Index: 521280 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.7850. Min Act: -0.1700
Data Index: 5398313 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2225. Min Range: -7.2225
Max Act: 6.7850. Min Act: -0.1700
Data Index: 6852930 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19