Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.6327. Min Act: -0.1700
Data Index: 4977083 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.5702. Min Act: -0.1700
Data Index: 260240 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.5389. Min Act: -0.1700
Data Index: 5567966 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.5077. Min Act: -0.1700
Data Index: 5268769 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.4452. Min Act: -0.1700
Data Index: 5700341 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.4452. Min Act: -0.1700
Data Index: 3122054 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.3827. Min Act: -0.1700
Data Index: 4740447 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.3202. Min Act: -0.1700
Data Index: 858397 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.3202. Min Act: -0.1700
Data Index: 3248428 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.3202. Min Act: -0.1700
Data Index: 5740865 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2889. Min Act: -0.1700
Data Index: 3171017 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2889. Min Act: -0.1700
Data Index: 2083188 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2577. Min Act: -0.1700
Data Index: 1154610 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2577. Min Act: -0.1700
Data Index: 2437521 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2264. Min Act: -0.1700
Data Index: 4820088 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2264. Min Act: -0.1700
Data Index: 6751023 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2264. Min Act: -0.1700
Data Index: 6031126 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2264. Min Act: -0.1700
Data Index: 4906134 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2264. Min Act: -0.1700
Data Index: 369183 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6327. Min Range: -5.6327
Max Act: 5.2264. Min Act: -0.1700
Data Index: 6751022 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19