Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1435 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.5148. Min Act: -0.1700
Data Index: 6461865 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.4523. Min Act: -0.1700
Data Index: 4138520 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.4211. Min Act: -0.1700
Data Index: 7913706 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.3273. Min Act: -0.1700
Data Index: 115599 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.2648. Min Act: -0.1700
Data Index: 1735448 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5033041 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.2023. Min Act: -0.1700
Data Index: 682853 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.2023. Min Act: -0.1700
Data Index: 1624720 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.1711. Min Act: -0.1700
Data Index: 3428954 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.1711. Min Act: -0.1700
Data Index: 988783 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.1398. Min Act: -0.1700
Data Index: 5204818 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.1398. Min Act: -0.1700
Data Index: 8186312 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.0773. Min Act: -0.1700
Data Index: 1783754 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.0461. Min Act: -0.1700
Data Index: 8218619 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.0148. Min Act: -0.1700
Data Index: 8599408 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.0148. Min Act: -0.1700
Data Index: 5019905 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5148. Min Range: -5.5148
Max Act: 5.0461. Min Act: -0.1700
Data Index: 7326407 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5148. Min Range: -5.5148
Max Act: 4.9836. Min Act: -0.1700
Data Index: 2614058 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5148. Min Range: -5.5148
Max Act: 4.9836. Min Act: -0.1700
Data Index: 2669661 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5148. Min Range: -5.5148
Max Act: 4.9836. Min Act: -0.1700
Data Index: 1155974 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19