Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1254 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3741. Min Act: -0.1700
Data Index: 1934653 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3577. Min Act: -0.1700
Data Index: 5365439 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3413. Min Act: -0.1700
Data Index: 2237897 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3577. Min Act: -0.1700
Data Index: 7470357 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3413. Min Act: -0.1700
Data Index: 5236157 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3413. Min Act: -0.1700
Data Index: 4772678 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3413. Min Act: -0.1700
Data Index: 7652506 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3413. Min Act: -0.1700
Data Index: 5490494 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3085. Min Act: -0.1700
Data Index: 48535 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3249. Min Act: -0.1700
Data Index: 6505155 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3249. Min Act: -0.1700
Data Index: 4189322 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3413. Min Act: -0.1700
Data Index: 3479956 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3249. Min Act: -0.1700
Data Index: 8208649 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3249. Min Act: -0.1700
Data Index: 2896419 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3085. Min Act: -0.1700
Data Index: 282870 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.2920. Min Act: -0.1700
Data Index: 3376613 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3085. Min Act: -0.1700
Data Index: 4315336 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.3085. Min Act: -0.1700
Data Index: 134080 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.2920. Min Act: -0.1700
Data Index: 7722959 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3741. Min Range: -2.3741
Max Act: 2.2920. Min Act: -0.1700
Data Index: 587763 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19