Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.8970. Min Act: -0.1700
Data Index: 2705856 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.6783. Min Act: -0.1700
Data Index: 7601428 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.5845. Min Act: -0.1700
Data Index: 3083479 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.5533. Min Act: -0.1700
Data Index: 8095476 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.4908. Min Act: -0.1700
Data Index: 3669297 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.4283. Min Act: -0.1700
Data Index: 4910219 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3345. Min Act: -0.1700
Data Index: 1217017 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3345. Min Act: -0.1700
Data Index: 4918773 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3033. Min Act: -0.1700
Data Index: 6941088 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3033. Min Act: -0.1700
Data Index: 7511193 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.3033. Min Act: -0.1700
Data Index: 2715448 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2720. Min Act: -0.1700
Data Index: 7517886 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2720. Min Act: -0.1700
Data Index: 5092416 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2720. Min Act: -0.1700
Data Index: 1387901 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2720. Min Act: -0.1700
Data Index: 6689181 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2720. Min Act: -0.1700
Data Index: 4848813 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2408. Min Act: -0.1700
Data Index: 1659343 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2408. Min Act: -0.1700
Data Index: 5248978 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2408. Min Act: -0.1700
Data Index: 8142082 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8970. Min Range: -6.8970
Max Act: 6.2095. Min Act: -0.1700
Data Index: 865689 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19