Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3799 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.7721. Min Act: -0.1700
Data Index: 4100115 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.6469. Min Act: -0.1700
Data Index: 4785544 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.6156. Min Act: -0.1700
Data Index: 3219627 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.5843. Min Act: -0.1700
Data Index: 71191 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.5530. Min Act: -0.1700
Data Index: 4100118 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.5530. Min Act: -0.1700
Data Index: 3264548 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.5217. Min Act: -0.1700
Data Index: 6073077 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.5217. Min Act: -0.1700
Data Index: 4435850 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.5217. Min Act: -0.1700
Data Index: 2817995 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.5217. Min Act: -0.1700
Data Index: 4100114 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4904. Min Act: -0.1700
Data Index: 4100110 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4747. Min Act: -0.1700
Data Index: 4100111 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4904. Min Act: -0.1700
Data Index: 33602 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4590. Min Act: -0.1700
Data Index: 5825052 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4590. Min Act: -0.1700
Data Index: 962271 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4590. Min Act: -0.1700
Data Index: 51775 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4434. Min Act: -0.1700
Data Index: 6056153 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4277. Min Act: -0.1700
Data Index: 8693600 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4277. Min Act: -0.1700
Data Index: 1922776 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7721. Min Range: -3.7721
Max Act: 3.4277. Min Act: -0.1700
Data Index: 6056190 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19