Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.2623. Min Act: -0.1700
Data Index: 5301407 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1998. Min Act: -0.1700
Data Index: 4577588 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1998. Min Act: -0.1700
Data Index: 6052960 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1686. Min Act: -0.1700
Data Index: 3021090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1686. Min Act: -0.1700
Data Index: 8694779 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1061. Min Act: -0.1700
Data Index: 7128229 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1373. Min Act: -0.1700
Data Index: 3031466 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1373. Min Act: -0.1698
Data Index: 7779249 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1373. Min Act: -0.1700
Data Index: 2072428 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1373. Min Act: -0.1700
Data Index: 3515369 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1061. Min Act: -0.1699
Data Index: 7182975 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0748. Min Act: -0.1700
Data Index: 4805603 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1061. Min Act: -0.1698
Data Index: 3256668 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0748. Min Act: -0.1698
Data Index: 1815891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.0748. Min Act: -0.1700
Data Index: 7659362 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1061. Min Act: -0.1700
Data Index: 1127609 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1061. Min Act: -0.1700
Data Index: 5761306 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1373. Min Act: -0.1698
Data Index: 7779251 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1061. Min Act: -0.1700
Data Index: 3949024 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2623. Min Range: -5.2623
Max Act: 5.1061. Min Act: -0.1698
Data Index: 5852252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19