Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 982 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.3890. Min Act: -0.1700
Data Index: 84910 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.3577. Min Act: -0.1700
Data Index: 8647333 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.3265. Min Act: -0.1700
Data Index: 8050669 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.3265. Min Act: -0.1700
Data Index: 8262189 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.2327. Min Act: -0.1700
Data Index: 1068444 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.1390. Min Act: -0.1700
Data Index: 847401 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.1077. Min Act: -0.1700
Data Index: 5908235 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.0765. Min Act: -0.1700
Data Index: 927430 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.1077. Min Act: -0.1700
Data Index: 6645063 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.0452. Min Act: -0.1700
Data Index: 1528292 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.0452. Min Act: -0.1700
Data Index: 867499 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.0452. Min Act: -0.1700
Data Index: 6982295 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3890. Min Range: -7.3890
Max Act: 7.0140. Min Act: -0.1700
Data Index: 2295098 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3890. Min Range: -7.3890
Max Act: 6.9827. Min Act: -0.1700
Data Index: 342053 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3890. Min Range: -7.3890
Max Act: 6.9515. Min Act: -0.1700
Data Index: 4213869 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3890. Min Range: -7.3890
Max Act: 6.9515. Min Act: -0.1700
Data Index: 3493578 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3890. Min Range: -7.3890
Max Act: 6.9515. Min Act: -0.1700
Data Index: 8524515 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3890. Min Range: -7.3890
Max Act: 6.9515. Min Act: -0.1700
Data Index: 4419252 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3890. Min Range: -7.3890
Max Act: 6.9202. Min Act: -0.1700
Data Index: 5172153 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3890. Min Range: -7.3890
Max Act: 6.9202. Min Act: -0.1700
Data Index: 6640050 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19