Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4020 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1330. Min Range: -7.1330
Max Act: 7.1330. Min Act: -0.1700
Data Index: 6506449 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1330. Min Range: -7.1330
Max Act: 7.1017. Min Act: -0.1700
Data Index: 6823282 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1330. Min Range: -7.1330
Max Act: 7.0705. Min Act: -0.1700
Data Index: 1389849 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1330. Min Range: -7.1330
Max Act: 7.0080. Min Act: -0.1700
Data Index: 3368512 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1330. Min Range: -7.1330
Max Act: 7.0392. Min Act: -0.1700
Data Index: 3996121 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.9767. Min Act: -0.1700
Data Index: 2944111 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.9767. Min Act: -0.1700
Data Index: 4477986 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.9142. Min Act: -0.1700
Data Index: 45747 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.9142. Min Act: -0.1700
Data Index: 2787908 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.8830. Min Act: -0.1700
Data Index: 7876792 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.8205. Min Act: -0.1700
Data Index: 1230362 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.8205. Min Act: -0.1700
Data Index: 2623572 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.8830. Min Act: -0.1700
Data Index: 6629397 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.7892. Min Act: -0.1700
Data Index: 7393072 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.8205. Min Act: -0.1700
Data Index: 583417 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.7892. Min Act: -0.1700
Data Index: 8580858 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.7580. Min Act: -0.1700
Data Index: 1310547 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.7267. Min Act: -0.1700
Data Index: 8660584 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.7580. Min Act: -0.1700
Data Index: 7373052 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1330. Min Range: -7.1330
Max Act: 6.7267. Min Act: -0.1700
Data Index: 1345686 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19