Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 547 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.6485. Min Act: -0.1700
Data Index: 8122587 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.5962. Min Act: -0.1700
Data Index: 3115626 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.5787. Min Act: -0.1700
Data Index: 2372358 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.5262. Min Act: -0.1700
Data Index: 6754544 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.5262. Min Act: -0.1700
Data Index: 829272 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.5086. Min Act: -0.1700
Data Index: 360853 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.5086. Min Act: -0.1700
Data Index: 6470975 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4910. Min Act: -0.1700
Data Index: 6760340 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4735. Min Act: -0.1700
Data Index: 39164 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4910. Min Act: -0.1700
Data Index: 691872 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.5086. Min Act: -0.1700
Data Index: 8250138 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4910. Min Act: -0.1700
Data Index: 7700905 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4735. Min Act: -0.1700
Data Index: 7715059 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4910. Min Act: -0.1700
Data Index: 1172497 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4735. Min Act: -0.1700
Data Index: 5488689 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4735. Min Act: -0.1700
Data Index: 430424 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4735. Min Act: -0.1700
Data Index: 1175607 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4735. Min Act: -0.1700
Data Index: 8638260 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4559. Min Act: -0.1700
Data Index: 7518316 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6485. Min Range: -1.6485
Max Act: 1.4383. Min Act: -0.1700
Data Index: 5902269 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19