Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0528. Min Range: -8.0528
Max Act: 8.0528. Min Act: -0.1700
Data Index: 6093433 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0528. Min Range: -8.0528
Max Act: 7.3341. Min Act: -0.1700
Data Index: 1439178 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0528. Min Range: -8.0528
Max Act: 7.2716. Min Act: -0.1700
Data Index: 552744 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0528. Min Range: -8.0528
Max Act: 7.0528. Min Act: -0.1700
Data Index: 8721394 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.9903. Min Act: -0.1700
Data Index: 6237981 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.9591. Min Act: -0.1700
Data Index: 8394113 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.9278. Min Act: -0.1700
Data Index: 6344915 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.8966. Min Act: -0.1700
Data Index: 2374054 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.8966. Min Act: -0.1700
Data Index: 8103138 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.8966. Min Act: -0.1700
Data Index: 3824189 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.8341. Min Act: -0.1700
Data Index: 162509 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.8341. Min Act: -0.1700
Data Index: 6634234 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.7091. Min Act: -0.1700
Data Index: 8220864 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.7403. Min Act: -0.1700
Data Index: 4988199 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.7403. Min Act: -0.1700
Data Index: 5659888 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.7091. Min Act: -0.1700
Data Index: 3559024 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.7403. Min Act: -0.1700
Data Index: 7196518 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.7091. Min Act: -0.1700
Data Index: 2908677 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.7091. Min Act: -0.1700
Data Index: 1286732 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0528. Min Range: -8.0528
Max Act: 6.6778. Min Act: -0.1700
Data Index: 6520112 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19