Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5213 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.8029. Min Act: -0.1700
Data Index: 51032 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.4116. Min Act: -0.1700
Data Index: 2400373 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.3959. Min Act: -0.1700
Data Index: 6012361 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.3645. Min Act: -0.1700
Data Index: 4180416 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.3488. Min Act: -0.1700
Data Index: 6461535 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.3174. Min Act: -0.1700
Data Index: 8816431 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.3331. Min Act: -0.1700
Data Index: 6494869 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.3174. Min Act: -0.1700
Data Index: 1246558 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2703. Min Act: -0.1700
Data Index: 3613908 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2389. Min Act: -0.1700
Data Index: 64351 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2389. Min Act: -0.1700
Data Index: 3353734 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2075. Min Act: -0.1700
Data Index: 5462939 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2075. Min Act: -0.1700
Data Index: 1910318 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.1918. Min Act: -0.1700
Data Index: 2985696 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2075. Min Act: -0.1700
Data Index: 518852 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2075. Min Act: -0.1700
Data Index: 3418808 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2075. Min Act: -0.1700
Data Index: 7074069 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.1918. Min Act: -0.1700
Data Index: 1138690 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.2075. Min Act: -0.1700
Data Index: 2797945 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8029. Min Range: -3.8029
Max Act: 3.1918. Min Act: -0.1700
Data Index: 3070884 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19