Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5577 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.4248. Min Act: -0.1700
Data Index: 3593675 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2998. Min Act: -0.1700
Data Index: 2526010 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2372. Min Act: -0.1700
Data Index: 3157076 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2060. Min Act: -0.1700
Data Index: 6736227 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2060. Min Act: -0.1700
Data Index: 3688357 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1747. Min Act: -0.1700
Data Index: 8785939 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1747. Min Act: -0.1700
Data Index: 1369541 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1747. Min Act: -0.1700
Data Index: 5846819 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1122. Min Act: -0.1700
Data Index: 4351649 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1435. Min Act: -0.1700
Data Index: 3936977 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1122. Min Act: -0.1700
Data Index: 1185987 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.1122. Min Act: -0.1700
Data Index: 3602021 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 3776782 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 3057672 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0810. Min Act: -0.1700
Data Index: 2809135 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0497. Min Act: -0.1700
Data Index: 8221869 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0497. Min Act: -0.1700
Data Index: 7939843 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0497. Min Act: -0.1700
Data Index: 2447462 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0185. Min Act: -0.1700
Data Index: 5982346 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.0497. Min Act: -0.1700
Data Index: 2423195 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19