Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2300 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0755. Min Range: -7.0755
Max Act: 7.0755. Min Act: -0.1700
Data Index: 3007553 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.6692. Min Act: -0.1700
Data Index: 419131 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.4817. Min Act: -0.1700
Data Index: 2993659 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.4192. Min Act: -0.1700
Data Index: 278094 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.3880. Min Act: -0.1700
Data Index: 1415801 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.3255. Min Act: -0.1700
Data Index: 7726649 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.3255. Min Act: -0.1700
Data Index: 3776985 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.2630. Min Act: -0.1700
Data Index: 4091691 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.2942. Min Act: -0.1700
Data Index: 2773926 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.2630. Min Act: -0.1700
Data Index: 520947 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.2005. Min Act: -0.1700
Data Index: 5325574 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.2005. Min Act: -0.1700
Data Index: 5562415 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.1692. Min Act: -0.1700
Data Index: 1018690 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.1380. Min Act: -0.1700
Data Index: 4065311 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.0755. Min Act: -0.1700
Data Index: 2185759 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.0442. Min Act: -0.1700
Data Index: 1936118 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.0755. Min Act: -0.1700
Data Index: 4287 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.0755. Min Act: -0.1700
Data Index: 4206132 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.0442. Min Act: -0.1700
Data Index: 6710068 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0755. Min Range: -7.0755
Max Act: 6.0130. Min Act: -0.1700
Data Index: 439948 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19