Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.2280. Min Act: -0.1700
Data Index: 7673953 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.1968. Min Act: -0.1700
Data Index: 8645503 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.1030. Min Act: -0.1700
Data Index: 3374213 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.1030. Min Act: -0.1700
Data Index: 6308568 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.1030. Min Act: -0.1700
Data Index: 8821404 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0718. Min Act: -0.1700
Data Index: 6442907 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0718. Min Act: -0.1700
Data Index: 3867661 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0093. Min Act: -0.1700
Data Index: 111284 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0405. Min Act: -0.1700
Data Index: 6524933 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0405. Min Act: -0.1700
Data Index: 1805410 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0405. Min Act: -0.1700
Data Index: 4104863 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0093. Min Act: -0.1700
Data Index: 1385867 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0093. Min Act: -0.1700
Data Index: 8277919 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0093. Min Act: -0.1700
Data Index: 2499775 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0093. Min Act: -0.1700
Data Index: 8800416 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2280. Min Range: -7.2280
Max Act: 7.0093. Min Act: -0.1700
Data Index: 4371364 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2280. Min Range: -7.2280
Max Act: 6.9780. Min Act: -0.1700
Data Index: 5529231 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2280. Min Range: -7.2280
Max Act: 6.9780. Min Act: -0.1700
Data Index: 3211552 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2280. Min Range: -7.2280
Max Act: 6.9780. Min Act: -0.1700
Data Index: 6315042 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2280. Min Range: -7.2280
Max Act: 6.9468. Min Act: -0.1700
Data Index: 4303353 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19