Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4645 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2869. Min Range: -6.2869
Max Act: 6.2869. Min Act: -0.1700
Data Index: 6826663 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.9431. Min Act: -0.1700
Data Index: 583541 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.8494. Min Act: -0.1700
Data Index: 3696869 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.7869. Min Act: -0.1700
Data Index: 1679966 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.7556. Min Act: -0.1700
Data Index: 2206523 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.7244. Min Act: -0.1700
Data Index: 5914629 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.7244. Min Act: -0.1700
Data Index: 1375298 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6931. Min Act: -0.1700
Data Index: 7537575 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6931. Min Act: -0.1700
Data Index: 6159906 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6931. Min Act: -0.1700
Data Index: 733375 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6931. Min Act: -0.1700
Data Index: 3004829 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6306. Min Act: -0.1700
Data Index: 298979 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6619. Min Act: -0.1699
Data Index: 7294897 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6619. Min Act: -0.1700
Data Index: 4362237 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6306. Min Act: -0.1700
Data Index: 85632 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6619. Min Act: -0.1700
Data Index: 5573849 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6306. Min Act: -0.1700
Data Index: 2180057 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6306. Min Act: -0.1700
Data Index: 3255732 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6306. Min Act: -0.1700
Data Index: 3698196 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2869. Min Range: -6.2869
Max Act: 5.6306. Min Act: -0.1700
Data Index: 6165777 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19