Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.2452. Min Act: -0.1700
Data Index: 8347046 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.2452. Min Act: -0.1700
Data Index: 6941244 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.2139. Min Act: -0.1700
Data Index: 4824266 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.2139. Min Act: -0.1700
Data Index: 7724722 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.2139. Min Act: -0.1700
Data Index: 1831920 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.2139. Min Act: -0.1700
Data Index: 6431694 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.2139. Min Act: -0.1700
Data Index: 511302 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0889. Min Act: -0.1700
Data Index: 5369127 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1826212 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.1202. Min Act: -0.1700
Data Index: 530801 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0889. Min Act: -0.1700
Data Index: 3669101 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0577. Min Act: -0.1700
Data Index: 7379346 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1081248 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0577. Min Act: -0.1700
Data Index: 8420807 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0577. Min Act: -0.1700
Data Index: 3181351 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2452. Min Range: -5.2452
Max Act: 4.9952. Min Act: -0.1700
Data Index: 1466146 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2452. Min Range: -5.2452
Max Act: 4.9952. Min Act: -0.1700
Data Index: 6918420 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2452. Min Range: -5.2452
Max Act: 5.0264. Min Act: -0.1700
Data Index: 7774402 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2452. Min Range: -5.2452
Max Act: 4.9639. Min Act: -0.1700
Data Index: 6713092 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2452. Min Range: -5.2452
Max Act: 4.9639. Min Act: -0.1700
Data Index: 3664965 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19