Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.5498. Min Act: -0.1700
Data Index: 4110518 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4873. Min Act: -0.1700
Data Index: 8579203 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4561. Min Act: -0.1700
Data Index: 3703312 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4561. Min Act: -0.1700
Data Index: 8453324 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4561. Min Act: -0.1700
Data Index: 6170931 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4561. Min Act: -0.1700
Data Index: 914650 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4248. Min Act: -0.1700
Data Index: 6911033 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4248. Min Act: -0.1700
Data Index: 368115 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4248. Min Act: -0.1700
Data Index: 482986 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3936. Min Act: -0.1700
Data Index: 6608259 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4248. Min Act: -0.1700
Data Index: 3421056 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3936. Min Act: -0.1700
Data Index: 7748890 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4248. Min Act: -0.1700
Data Index: 6377252 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.4561. Min Act: -0.1700
Data Index: 4128340 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3936. Min Act: -0.1700
Data Index: 8544106 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3936. Min Act: -0.1700
Data Index: 7286619 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3936. Min Act: -0.1700
Data Index: 7656761 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3311. Min Act: -0.1700
Data Index: 7829535 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3311. Min Act: -0.1700
Data Index: 108601 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5498. Min Range: -4.5498
Max Act: 4.3936. Min Act: -0.1700
Data Index: 8145504 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19