Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.3732. Min Act: -0.1700
Data Index: 8822464 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.2795. Min Act: -0.1700
Data Index: 8822463 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3732. Min Range: -7.3732
Max Act: 7.0295. Min Act: -0.1700
Data Index: 7315601 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9982. Min Act: -0.1700
Data Index: 7776427 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9357. Min Act: -0.1700
Data Index: 858249 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.9045. Min Act: -0.1700
Data Index: 3686515 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8732. Min Act: -0.1700
Data Index: 480526 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8732. Min Act: -0.1700
Data Index: 3726960 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8107. Min Act: -0.1700
Data Index: 224372 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8107. Min Act: -0.1700
Data Index: 864816 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.8420. Min Act: -0.1700
Data Index: 2849695 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.7795. Min Act: -0.1700
Data Index: 1201602 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.7795. Min Act: -0.1700
Data Index: 698256 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.7170. Min Act: -0.1700
Data Index: 4887871 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.6857. Min Act: -0.1700
Data Index: 6387618 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.6857. Min Act: -0.1700
Data Index: 7959107 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.6857. Min Act: -0.1700
Data Index: 8273316 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.6857. Min Act: -0.1700
Data Index: 5757785 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.6545. Min Act: -0.1700
Data Index: 3740354 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3732. Min Range: -7.3732
Max Act: 6.6545. Min Act: -0.1700
Data Index: 1496696 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19