Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5952 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3075. Min Range: -9.3075
Max Act: 9.3075. Min Act: -0.1700
Data Index: 5713319 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.8700. Min Act: -0.1700
Data Index: 2435020 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.6825. Min Act: -0.1700
Data Index: 2882339 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.6825. Min Act: -0.1700
Data Index: 5257041 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.4950. Min Act: -0.1700
Data Index: 325818 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.4950. Min Act: -0.1700
Data Index: 6842174 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.3700. Min Act: -0.1700
Data Index: 2802527 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.3700. Min Act: -0.1700
Data Index: 5198856 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.3075. Min Act: -0.1700
Data Index: 6008564 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.3075. Min Act: -0.1700
Data Index: 2699942 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.2450. Min Act: -0.1700
Data Index: 3938110 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.2450. Min Act: -0.1700
Data Index: 5730547 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.1825. Min Act: -0.1700
Data Index: 3526279 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.1200. Min Act: -0.1700
Data Index: 240891 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.1825. Min Act: -0.1700
Data Index: 5989276 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.1200. Min Act: -0.1700
Data Index: 6309462 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.1200. Min Act: -0.1700
Data Index: 4138283 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.1200. Min Act: -0.1700
Data Index: 2409960 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.0575. Min Act: -0.1700
Data Index: 4743488 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3075. Min Range: -9.3075
Max Act: 8.0575. Min Act: -0.1700
Data Index: 3797956 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19