Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.6466. Min Act: -0.1700
Data Index: 2164784 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.6466. Min Act: -0.1700
Data Index: 2192066 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.6154. Min Act: -0.1700
Data Index: 3527680 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.5529. Min Act: -0.1700
Data Index: 988468 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.5841. Min Act: -0.1700
Data Index: 2080349 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.4904. Min Act: -0.1700
Data Index: 1853857 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.4591. Min Act: -0.1700
Data Index: 2694377 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.4279. Min Act: -0.1700
Data Index: 1630364 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3966. Min Act: -0.1700
Data Index: 8701992 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3654. Min Act: -0.1700
Data Index: 408685 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3654. Min Act: -0.1700
Data Index: 3708957 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3654. Min Act: -0.1700
Data Index: 2837450 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3654. Min Act: -0.1700
Data Index: 1234990 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3654. Min Act: -0.1700
Data Index: 7642713 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3029. Min Act: -0.1700
Data Index: 3550251 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3029. Min Act: -0.1700
Data Index: 1223557 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.2716. Min Act: -0.1700
Data Index: 7482662 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3029. Min Act: -0.1700
Data Index: 4693063 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.3341. Min Act: -0.1700
Data Index: 4005426 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6466. Min Range: -4.6466
Max Act: 4.2716. Min Act: -0.1700
Data Index: 5333262 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19