Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0197. Min Range: -4.0197
Max Act: 4.0197. Min Act: -0.1700
Data Index: 4338957 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.9885. Min Act: -0.1700
Data Index: 6568628 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.9260. Min Act: -0.1700
Data Index: 7939267 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.8634. Min Act: -0.1700
Data Index: 1355177 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.8634. Min Act: -0.1700
Data Index: 604632 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.8321. Min Act: -0.1700
Data Index: 1876937 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7696. Min Act: -0.1700
Data Index: 1991008 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7696. Min Act: -0.1700
Data Index: 4868226 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7383. Min Act: -0.1700
Data Index: 2438671 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7383. Min Act: -0.1700
Data Index: 6418569 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7070. Min Act: -0.1700
Data Index: 7727219 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7383. Min Act: -0.1700
Data Index: 4386528 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7070. Min Act: -0.1700
Data Index: 161353 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7070. Min Act: -0.1700
Data Index: 1162832 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7070. Min Act: -0.1700
Data Index: 3210175 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.7070. Min Act: -0.1700
Data Index: 8415173 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.6758. Min Act: -0.1700
Data Index: 7397015 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.6445. Min Act: -0.1700
Data Index: 8610302 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.6758. Min Act: -0.1700
Data Index: 839638 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0197. Min Range: -4.0197
Max Act: 3.6445. Min Act: -0.1700
Data Index: 34630 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19