Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.3444. Min Act: -0.1700
Data Index: 7652835 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.2819. Min Act: -0.1700
Data Index: 7855100 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.2194. Min Act: -0.1700
Data Index: 8614652 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.2194. Min Act: -0.1700
Data Index: 8330890 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.2194. Min Act: -0.1700
Data Index: 5510000 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.2194. Min Act: -0.1700
Data Index: 6989238 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1882. Min Act: -0.1700
Data Index: 6653807 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1882. Min Act: -0.1700
Data Index: 8400530 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1882. Min Act: -0.1700
Data Index: 2930424 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1569. Min Act: -0.1700
Data Index: 436292 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1569. Min Act: -0.1700
Data Index: 3612818 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1569. Min Act: -0.1700
Data Index: 8802411 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1569. Min Act: -0.1700
Data Index: 3258752 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1569. Min Act: -0.1700
Data Index: 3233555 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1882. Min Act: -0.1700
Data Index: 2931262 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1882. Min Act: -0.1700
Data Index: 5154415 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.0944. Min Act: -0.1700
Data Index: 2118674 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.0944. Min Act: -0.1700
Data Index: 6094795 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.1257. Min Act: -0.1700
Data Index: 3708146 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3444. Min Range: -5.3444
Max Act: 5.0944. Min Act: -0.1700
Data Index: 827062 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19