Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4104 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.8105. Min Act: -0.1700
Data Index: 7630241 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.6228. Min Act: -0.1700
Data Index: 2810888 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5602. Min Act: -0.1700
Data Index: 6184851 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5915. Min Act: -0.1700
Data Index: 1235609 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5915. Min Act: -0.1700
Data Index: 1508256 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5602. Min Act: -0.1700
Data Index: 2933254 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5602. Min Act: -0.1700
Data Index: 4432541 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5602. Min Act: -0.1700
Data Index: 7324068 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4976. Min Act: -0.1700
Data Index: 7457106 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5289. Min Act: -0.1700
Data Index: 1519548 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.5289. Min Act: -0.1700
Data Index: 2281497 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4976. Min Act: -0.1700
Data Index: 5641071 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4976. Min Act: -0.1700
Data Index: 2611383 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4662. Min Act: -0.1700
Data Index: 4924048 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4662. Min Act: -0.1700
Data Index: 1692570 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4349. Min Act: -0.1700
Data Index: 4746164 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4662. Min Act: -0.1700
Data Index: 4566593 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4662. Min Act: -0.1700
Data Index: 4457349 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4662. Min Act: -0.1700
Data Index: 4184937 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8105. Min Range: -3.8105
Max Act: 3.4662. Min Act: -0.1700
Data Index: 6362039 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19