Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3977. Min Range: -5.3977
Max Act: 5.3977. Min Act: -0.1700
Data Index: 6803874 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3977. Min Range: -5.3977
Max Act: 5.0227. Min Act: -0.1700
Data Index: 954708 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3977. Min Range: -5.3977
Max Act: 5.0227. Min Act: -0.1700
Data Index: 482033 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.9914. Min Act: -0.1700
Data Index: 3306223 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.9602. Min Act: -0.1700
Data Index: 1160155 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.9289. Min Act: -0.1700
Data Index: 6141116 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.9289. Min Act: -0.1700
Data Index: 8565025 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8977. Min Act: -0.1700
Data Index: 7144487 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8664. Min Act: -0.1700
Data Index: 430414 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8664. Min Act: -0.1700
Data Index: 253396 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8664. Min Act: -0.1700
Data Index: 6325117 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8664. Min Act: -0.1700
Data Index: 2420676 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8352. Min Act: -0.1700
Data Index: 5303773 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8352. Min Act: -0.1700
Data Index: 20639 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8039. Min Act: -0.1700
Data Index: 1219079 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8039. Min Act: -0.1700
Data Index: 3333743 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8039. Min Act: -0.1700
Data Index: 8656167 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8039. Min Act: -0.1700
Data Index: 6153993 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.8039. Min Act: -0.1700
Data Index: 7555051 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3977. Min Range: -5.3977
Max Act: 4.7727. Min Act: -0.1700
Data Index: 2507285 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19