Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.6795. Min Act: -0.1700
Data Index: 3049497 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.5545. Min Act: -0.1700
Data Index: 2777961 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.5233. Min Act: -0.1700
Data Index: 6754202 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.5233. Min Act: -0.1700
Data Index: 5264191 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.4920. Min Act: -0.1700
Data Index: 3399919 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.4295. Min Act: -0.1700
Data Index: 8425517 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.4295. Min Act: -0.1700
Data Index: 2224863 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3983. Min Act: -0.1700
Data Index: 6954323 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3983. Min Act: -0.1700
Data Index: 5778844 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3670. Min Act: -0.1700
Data Index: 6364153 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3358. Min Act: -0.1700
Data Index: 22414 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3358. Min Act: -0.1700
Data Index: 5713534 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3358. Min Act: -0.1700
Data Index: 2179469 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.2733. Min Act: -0.1700
Data Index: 2308079 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3045. Min Act: -0.1700
Data Index: 4739768 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.3045. Min Act: -0.1700
Data Index: 7227866 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.2733. Min Act: -0.1700
Data Index: 50348 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.2420. Min Act: -0.1700
Data Index: 4562094 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.2733. Min Act: -0.1700
Data Index: 4554955 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6795. Min Range: -7.6795
Max Act: 7.2733. Min Act: -0.1700
Data Index: 6505705 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19