Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.9395. Min Act: -0.1700
Data Index: 3045604 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.9395. Min Act: -0.1700
Data Index: 8720116 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.8770. Min Act: -0.1700
Data Index: 3814396 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.8145. Min Act: -0.1700
Data Index: 7976652 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.8145. Min Act: -0.1700
Data Index: 3744616 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.8145. Min Act: -0.1700
Data Index: 7986553 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.7208. Min Act: -0.1700
Data Index: 7192545 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.7208. Min Act: -0.1700
Data Index: 5062341 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.7208. Min Act: -0.1700
Data Index: 3223526 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6895. Min Act: -0.1700
Data Index: 4365229 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6895. Min Act: -0.1700
Data Index: 4584252 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6270. Min Act: -0.1700
Data Index: 7251316 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6583. Min Act: -0.1700
Data Index: 6988944 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6583. Min Act: -0.1700
Data Index: 3654885 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6583. Min Act: -0.1700
Data Index: 1214076 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6270. Min Act: -0.1700
Data Index: 2522302 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6270. Min Act: -0.1700
Data Index: 2777267 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.6270. Min Act: -0.1700
Data Index: 785842 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.5958. Min Act: -0.1700
Data Index: 772287 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9395. Min Range: -5.9395
Max Act: 5.5645. Min Act: -0.1700
Data Index: 970595 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19