Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1934 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0312. Min Range: -4.0312
Max Act: 4.0312. Min Act: -0.1700
Data Index: 2242686 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9999. Min Act: -0.1700
Data Index: 5880850 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9999. Min Act: -0.1700
Data Index: 3569232 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9999. Min Act: -0.1700
Data Index: 5611201 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9999. Min Act: -0.1700
Data Index: 1780268 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9999. Min Act: -0.1700
Data Index: 7651288 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9687. Min Act: -0.1700
Data Index: 5493780 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9687. Min Act: -0.1700
Data Index: 237087 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9687. Min Act: -0.1700
Data Index: 1629416 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9999. Min Act: -0.1700
Data Index: 3641233 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9999. Min Act: -0.1700
Data Index: 1535327 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9374. Min Act: -0.1700
Data Index: 3286589 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9687. Min Act: -0.1700
Data Index: 7525516 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9374. Min Act: -0.1700
Data Index: 1236727 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9374. Min Act: -0.1700
Data Index: 2763556 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9687. Min Act: -0.1700
Data Index: 2487770 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9374. Min Act: -0.1700
Data Index: 1118675 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9061. Min Act: -0.1700
Data Index: 522177 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9374. Min Act: -0.1700
Data Index: 4881008 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0312. Min Range: -4.0312
Max Act: 3.9374. Min Act: -0.1700
Data Index: 3451490 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19