Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4467 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.3156. Min Act: -0.1700
Data Index: 3506987 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 852395 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 4287748 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.2531. Min Act: -0.1700
Data Index: 6325670 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.2219. Min Act: -0.1700
Data Index: 526919 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.2219. Min Act: -0.1700
Data Index: 1675708 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.1906. Min Act: -0.1700
Data Index: 7253881 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.1906. Min Act: -0.1700
Data Index: 4782237 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0969. Min Act: -0.1700
Data Index: 1456115 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.1281. Min Act: -0.1700
Data Index: 8299818 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.1281. Min Act: -0.1700
Data Index: 1921523 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.1281. Min Act: -0.1700
Data Index: 7286899 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.1281. Min Act: -0.1700
Data Index: 170184 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0969. Min Act: -0.1700
Data Index: 988244 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0969. Min Act: -0.1700
Data Index: 7343182 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0969. Min Act: -0.1700
Data Index: 7881556 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0969. Min Act: -0.1700
Data Index: 2172277 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0656. Min Act: -0.1700
Data Index: 1544749 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0656. Min Act: -0.1700
Data Index: 4314313 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3156. Min Range: -5.3156
Max Act: 5.0969. Min Act: -0.1700
Data Index: 4495565 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19