Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1596 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.8743. Min Act: -0.1700
Data Index: 4225832 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.8430. Min Act: -0.1700
Data Index: 2970358 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.8430. Min Act: -0.1700
Data Index: 4659385 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.8430. Min Act: -0.1700
Data Index: 19645 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.8118. Min Act: -0.1700
Data Index: 4541778 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.8118. Min Act: -0.1700
Data Index: 4405415 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7805. Min Act: -0.1700
Data Index: 2047930 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7805. Min Act: -0.1700
Data Index: 5337 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7493. Min Act: -0.1700
Data Index: 1449105 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7180. Min Act: -0.1700
Data Index: 5083572 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7805. Min Act: -0.1700
Data Index: 8765495 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7493. Min Act: -0.1700
Data Index: 7393098 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7493. Min Act: -0.1700
Data Index: 1160492 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7493. Min Act: -0.1700
Data Index: 7960190 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7180. Min Act: -0.1700
Data Index: 6086357 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7180. Min Act: -0.1700
Data Index: 150831 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7180. Min Act: -0.1700
Data Index: 1588646 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.6868. Min Act: -0.1700
Data Index: 2273049 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4649720 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8743. Min Range: -5.8743
Max Act: 5.7180. Min Act: -0.1700
Data Index: 1449100 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19