Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5278 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3281. Min Range: -5.3281
Max Act: 5.3281. Min Act: -0.1700
Data Index: 5006160 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3281. Min Range: -5.3281
Max Act: 5.2656. Min Act: -0.1700
Data Index: 2643055 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3281. Min Range: -5.3281
Max Act: 5.2343. Min Act: -0.1700
Data Index: 916350 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3281. Min Range: -5.3281
Max Act: 5.1093. Min Act: -0.1700
Data Index: 5840301 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3281. Min Range: -5.3281
Max Act: 5.0468. Min Act: -0.1700
Data Index: 2109765 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.9843. Min Act: -0.1700
Data Index: 2047011 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.9531. Min Act: -0.1700
Data Index: 1827981 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.9218. Min Act: -0.1700
Data Index: 6310996 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8906. Min Act: -0.1700
Data Index: 2853710 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.9531. Min Act: -0.1700
Data Index: 7652901 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.9218. Min Act: -0.1700
Data Index: 8248359 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.9218. Min Act: -0.1700
Data Index: 2952954 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8906. Min Act: -0.1700
Data Index: 1605847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8906. Min Act: -0.1700
Data Index: 2193336 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8906. Min Act: -0.1700
Data Index: 3509825 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8906. Min Act: -0.1700
Data Index: 3676981 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8593. Min Act: -0.1700
Data Index: 7525563 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8593. Min Act: -0.1700
Data Index: 6916250 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8593. Min Act: -0.1700
Data Index: 3728249 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3281. Min Range: -5.3281
Max Act: 4.8593. Min Act: -0.1700
Data Index: 4100344 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19