Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 832 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0815. Min Range: -6.0815
Max Act: 6.0815. Min Act: -0.1700
Data Index: 3159938 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0815. Min Range: -6.0815
Max Act: 6.0190. Min Act: -0.1700
Data Index: 3064281 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0815. Min Range: -6.0815
Max Act: 6.0502. Min Act: -0.1700
Data Index: 4569811 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3159933 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3581183 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.8627. Min Act: -0.1700
Data Index: 2990328 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.9252. Min Act: -0.1700
Data Index: 414702 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.9252. Min Act: -0.1700
Data Index: 3031839 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.8315. Min Act: -0.1700
Data Index: 5017531 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.8002. Min Act: -0.1700
Data Index: 5811226 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7065. Min Act: -0.1700
Data Index: 3982258 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7690. Min Act: -0.1700
Data Index: 3730396 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7690. Min Act: -0.1700
Data Index: 2493877 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.8315. Min Act: -0.1700
Data Index: 5176820 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7065. Min Act: -0.1700
Data Index: 1218557 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7377. Min Act: -0.1700
Data Index: 90541 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7065. Min Act: -0.1700
Data Index: 4429428 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7065. Min Act: -0.1700
Data Index: 940856 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7377. Min Act: -0.1700
Data Index: 77143 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0815. Min Range: -6.0815
Max Act: 5.7065. Min Act: -0.1700
Data Index: 2591796 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19