Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.9305. Min Act: -0.1700
Data Index: 7629350 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.9135. Min Act: -0.1699
Data Index: 1234560 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8793. Min Act: -0.1700
Data Index: 2879562 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8964. Min Act: -0.1700
Data Index: 7179428 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8793. Min Act: -0.1693
Data Index: 8348859 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8622. Min Act: -0.1698
Data Index: 5028609 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8622. Min Act: -0.1700
Data Index: 903762 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8622. Min Act: -0.1699
Data Index: 7500524 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8622. Min Act: -0.1698
Data Index: 2643966 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8622. Min Act: -0.1689
Data Index: 5798622 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8451. Min Act: -0.1700
Data Index: 8333058 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8280. Min Act: -0.1695
Data Index: 2017741 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8280. Min Act: -0.1700
Data Index: 6468595 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8280. Min Act: -0.1700
Data Index: 3637455 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8194. Min Act: -0.1679
Data Index: 1505611 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8022. Min Act: -0.1694
Data Index: 547661 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8108. Min Act: -0.1700
Data Index: 3127589 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8108. Min Act: -0.1700
Data Index: 4315710 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8108. Min Act: -0.1700
Data Index: 359040 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9305. Min Range: -1.9305
Max Act: 1.8108. Min Act: -0.1700
Data Index: 7756955 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19