Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4856. Min Act: -0.1700
Data Index: 2263479 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4856. Min Act: -0.1700
Data Index: 6450179 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4856. Min Act: -0.1700
Data Index: 1012490 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4543. Min Act: -0.1700
Data Index: 1183994 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4231. Min Act: -0.1700
Data Index: 2263494 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4231. Min Act: -0.1700
Data Index: 6829514 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3918. Min Act: -0.1700
Data Index: 696115 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4231. Min Act: -0.1700
Data Index: 8624765 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3918. Min Act: -0.1700
Data Index: 3166855 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3918. Min Act: -0.1700
Data Index: 1012489 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3606. Min Act: -0.1700
Data Index: 2812630 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3606. Min Act: -0.1700
Data Index: 950493 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3293. Min Act: -0.1700
Data Index: 792046 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3293. Min Act: -0.1700
Data Index: 872663 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3293. Min Act: -0.1700
Data Index: 8703327 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3293. Min Act: -0.1700
Data Index: 7910354 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3293. Min Act: -0.1700
Data Index: 714936 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2981. Min Act: -0.1700
Data Index: 6439416 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2981. Min Act: -0.1700
Data Index: 7732731 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2981. Min Act: -0.1700
Data Index: 4305273 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19