Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.5091. Min Act: -0.1700
Data Index: 7618337 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.1966. Min Act: -0.1700
Data Index: 8206685 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.1341. Min Act: -0.1700
Data Index: 4667429 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.0716. Min Act: -0.1700
Data Index: 6200688 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.1029. Min Act: -0.1700
Data Index: 6230362 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.0716. Min Act: -0.1700
Data Index: 3087036 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.0404. Min Act: -0.1700
Data Index: 6635363 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5091. Min Range: -6.5091
Max Act: 6.0404. Min Act: -0.1700
Data Index: 3028180 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.9466. Min Act: -0.1700
Data Index: 4141231 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.9154. Min Act: -0.1700
Data Index: 8295958 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.9154. Min Act: -0.1700
Data Index: 1583329 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.9154. Min Act: -0.1700
Data Index: 6083990 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.8216. Min Act: -0.1700
Data Index: 6959035 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.7904. Min Act: -0.1700
Data Index: 5768106 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.7279. Min Act: -0.1700
Data Index: 8393144 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.7279. Min Act: -0.1700
Data Index: 8064010 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.6966. Min Act: -0.1700
Data Index: 2939214 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.6966. Min Act: -0.1700
Data Index: 4951982 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.6654. Min Act: -0.1700
Data Index: 5181568 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5091. Min Range: -6.5091
Max Act: 5.6654. Min Act: -0.1700
Data Index: 4105477 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19