Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.3297. Min Act: -0.1700
Data Index: 351329 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.3297. Min Act: -0.1700
Data Index: 2475099 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2359. Min Act: -0.1700
Data Index: 8610704 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2672. Min Act: -0.1700
Data Index: 4450314 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2498375 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2359. Min Act: -0.1700
Data Index: 6265300 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2359. Min Act: -0.1700
Data Index: 2089340 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2047. Min Act: -0.1700
Data Index: 8755601 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2832341 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.2047. Min Act: -0.1700
Data Index: 5933115 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1422. Min Act: -0.1700
Data Index: 6668088 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1422. Min Act: -0.1700
Data Index: 6701136 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1734. Min Act: -0.1700
Data Index: 6926394 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1734. Min Act: -0.1700
Data Index: 7494472 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1734. Min Act: -0.1700
Data Index: 828621 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1422. Min Act: -0.1700
Data Index: 6516495 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1109. Min Act: -0.1700
Data Index: 4661227 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1422. Min Act: -0.1700
Data Index: 763868 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1422. Min Act: -0.1700
Data Index: 7802000 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3297. Min Range: -5.3297
Max Act: 5.1109. Min Act: -0.1700
Data Index: 8456685 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19