Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.9804. Min Act: -0.1700
Data Index: 3117316 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.9487. Min Act: -0.1700
Data Index: 3117318 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.9645. Min Act: -0.1700
Data Index: 6075436 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.9487. Min Act: -0.1700
Data Index: 7002636 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.9170. Min Act: -0.1700
Data Index: 625651 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8853. Min Act: -0.1700
Data Index: 2663891 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8536. Min Act: -0.1700
Data Index: 2916481 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8377. Min Act: -0.1700
Data Index: 8829723 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8377. Min Act: -0.1700
Data Index: 7333255 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8218. Min Act: -0.1700
Data Index: 3061583 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8218. Min Act: -0.1700
Data Index: 2528205 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8059. Min Act: -0.1700
Data Index: 3657378 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.8218. Min Act: -0.1700
Data Index: 2108025 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.7740. Min Act: -0.1700
Data Index: 3657379 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.7261. Min Act: -0.1700
Data Index: 66396 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.7581. Min Act: -0.1700
Data Index: 350308 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.7261. Min Act: -0.1700
Data Index: 7716731 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.6941. Min Act: -0.1700
Data Index: 3990064 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.7101. Min Act: -0.1700
Data Index: 3699820 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9804. Min Range: -2.9804
Max Act: 2.6781. Min Act: -0.1700
Data Index: 4929553 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19