Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.2571. Min Act: -0.1700
Data Index: 5461248 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.1242. Min Act: -0.1699
Data Index: 2244712 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.0404. Min Act: -0.1700
Data Index: 6923984 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.0572. Min Act: -0.1700
Data Index: 2274109 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.0235. Min Act: -0.1700
Data Index: 8328390 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.0066. Min Act: -0.1700
Data Index: 2934559 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9897. Min Act: -0.1700
Data Index: 5671845 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.0066. Min Act: -0.1700
Data Index: 2762568 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2571. Min Range: -2.2571
Max Act: 2.0066. Min Act: -0.1700
Data Index: 3297351 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9897. Min Act: -0.1700
Data Index: 4751029 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9897. Min Act: -0.1700
Data Index: 5018107 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9897. Min Act: -0.1700
Data Index: 3923842 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9728. Min Act: -0.1700
Data Index: 1407971 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9728. Min Act: -0.1700
Data Index: 8230303 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9559. Min Act: -0.1700
Data Index: 7723981 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9728. Min Act: -0.1697
Data Index: 4959171 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9897. Min Act: -0.1700
Data Index: 5867158 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9728. Min Act: -0.1700
Data Index: 5315994 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9728. Min Act: -0.1700
Data Index: 3251420 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2571. Min Range: -2.2571
Max Act: 1.9559. Min Act: -0.1699
Data Index: 596898 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19