Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3701. Min Range: -10.3701
Max Act: 10.3701. Min Act: -0.1700
Data Index: 856505 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3701. Min Range: -10.3701
Max Act: 10.1201. Min Act: -0.1700
Data Index: 1929963 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3701. Min Range: -10.3701
Max Act: 10.0576. Min Act: -0.1700
Data Index: 4272139 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.8701. Min Act: -0.1700
Data Index: 1884738 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.8701. Min Act: -0.1700
Data Index: 3533974 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.8701. Min Act: -0.1700
Data Index: 3601190 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.8076. Min Act: -0.1700
Data Index: 3524230 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.7451. Min Act: -0.1700
Data Index: 6339392 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.7451. Min Act: -0.1700
Data Index: 8009319 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.6826. Min Act: -0.1700
Data Index: 7440811 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.6826. Min Act: -0.1700
Data Index: 5713657 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.6826. Min Act: -0.1700
Data Index: 6925801 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.6201. Min Act: -0.1700
Data Index: 3052605 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.6201. Min Act: -0.1700
Data Index: 5496184 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.5576. Min Act: -0.1700
Data Index: 7591030 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.5576. Min Act: -0.1700
Data Index: 4595160 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.4951. Min Act: -0.1700
Data Index: 1175852 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.5576. Min Act: -0.1700
Data Index: 6221300 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.4951. Min Act: -0.1700
Data Index: 4295435 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3701. Min Range: -10.3701
Max Act: 9.4951. Min Act: -0.1700
Data Index: 1969948 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19