Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.6139. Min Act: -0.1700
Data Index: 8074407 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5200. Min Act: -0.1700
Data Index: 1303014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 5029511 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5200. Min Act: -0.1699
Data Index: 2749913 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5200. Min Act: -0.1700
Data Index: 671541 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5200. Min Act: -0.1700
Data Index: 1060402 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 3351267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 805617 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 5312424 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4573. Min Act: -0.1700
Data Index: 278381 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1695
Data Index: 3748510 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 6368301 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1688
Data Index: 6484297 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.5200. Min Act: -0.1699
Data Index: 3104981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 1555533 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 2814092 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 6517329 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 1883319 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 6533262 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6139. Min Range: -3.6139
Max Act: 3.4887. Min Act: -0.1700
Data Index: 2872191 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19