Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4171 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.4245. Min Act: -0.1700
Data Index: 2712739 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.3620. Min Act: -0.1700
Data Index: 5468090 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.3308. Min Act: -0.1700
Data Index: 8780745 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.3308. Min Act: -0.1700
Data Index: 5418575 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.2995. Min Act: -0.1700
Data Index: 4660081 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.2995. Min Act: -0.1700
Data Index: 1393522 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.2683. Min Act: -0.1700
Data Index: 1780991 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.2370. Min Act: -0.1700
Data Index: 3737759 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.2058. Min Act: -0.1700
Data Index: 5746041 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1745. Min Act: -0.1700
Data Index: 7224944 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1745. Min Act: -0.1700
Data Index: 8134524 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.2058. Min Act: -0.1700
Data Index: 1929183 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1720153 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1120. Min Act: -0.1700
Data Index: 7284166 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1120. Min Act: -0.1700
Data Index: 713759 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1120. Min Act: -0.1700
Data Index: 4011572 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1120. Min Act: -0.1700
Data Index: 2893942 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1120. Min Act: -0.1700
Data Index: 6808586 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.1120. Min Act: -0.1700
Data Index: 3294316 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4245. Min Range: -5.4245
Max Act: 5.0808. Min Act: -0.1700
Data Index: 2557079 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19