Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.9391. Min Act: -0.1700
Data Index: 8590300 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.9391. Min Act: -0.1700
Data Index: 2458336 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.8922. Min Act: -0.1700
Data Index: 1476260 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.8922. Min Act: -0.1700
Data Index: 2936437 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.8140. Min Act: -0.1700
Data Index: 521855 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7984. Min Act: -0.1700
Data Index: 6771922 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7671. Min Act: -0.1700
Data Index: 1117589 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7828. Min Act: -0.1700
Data Index: 5217002 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7828. Min Act: -0.1700
Data Index: 1549271 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7515. Min Act: -0.1700
Data Index: 6526448 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7515. Min Act: -0.1700
Data Index: 2115691 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7358. Min Act: -0.1700
Data Index: 7037785 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7358. Min Act: -0.1700
Data Index: 7724201 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7358. Min Act: -0.1700
Data Index: 1082143 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7046. Min Act: -0.1700
Data Index: 1097550 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7202. Min Act: -0.1700
Data Index: 5217003 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7046. Min Act: -0.1700
Data Index: 1659180 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7202. Min Act: -0.1700
Data Index: 2895684 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.7046. Min Act: -0.1700
Data Index: 6000817 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9391. Min Range: -3.9391
Max Act: 3.6733. Min Act: -0.1700
Data Index: 1975331 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19