Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2273 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.8083. Min Act: -0.1697
Data Index: 3063663 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.7393. Min Act: -0.1699
Data Index: 8127582 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.7047. Min Act: -0.1700
Data Index: 3471105 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6526. Min Act: -0.1700
Data Index: 525657 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6700. Min Act: -0.1700
Data Index: 2304535 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6177. Min Act: -0.1698
Data Index: 2371391 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6351. Min Act: -0.1700
Data Index: 5981141 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6351. Min Act: -0.1700
Data Index: 2251507 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6177. Min Act: -0.1700
Data Index: 3313947 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6003. Min Act: -0.1699
Data Index: 8370297 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6177. Min Act: -0.1699
Data Index: 4977531 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6177. Min Act: -0.1695
Data Index: 5717876 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.5828. Min Act: -0.1700
Data Index: 5533948 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6003. Min Act: -0.1700
Data Index: 721311 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.6003. Min Act: -0.1700
Data Index: 8155719 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.5653. Min Act: -0.1700
Data Index: 2751480 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.5653. Min Act: -0.1700
Data Index: 936498 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.5828. Min Act: -0.1700
Data Index: 1381645 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.5653. Min Act: -0.1700
Data Index: 7682425 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8083. Min Range: -1.8083
Max Act: 1.5478. Min Act: -0.1700
Data Index: 5488900 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19