Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5269 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3356. Min Range: -6.3356
Max Act: 6.3356. Min Act: -0.1700
Data Index: 592487 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3356. Min Range: -6.3356
Max Act: 6.2419. Min Act: -0.1700
Data Index: 25882 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3356. Min Range: -6.3356
Max Act: 6.0856. Min Act: -0.1700
Data Index: 1822195 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3356. Min Range: -6.3356
Max Act: 6.1169. Min Act: -0.1700
Data Index: 144953 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3356. Min Range: -6.3356
Max Act: 6.0544. Min Act: -0.1700
Data Index: 282032 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3356. Min Range: -6.3356
Max Act: 6.0231. Min Act: -0.1700
Data Index: 5288267 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.9606. Min Act: -0.1700
Data Index: 7830700 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.9294. Min Act: -0.1700
Data Index: 5232963 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.9606. Min Act: -0.1700
Data Index: 5200938 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.9606. Min Act: -0.1700
Data Index: 7338892 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.9294. Min Act: -0.1700
Data Index: 6217854 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8981. Min Act: -0.1700
Data Index: 849995 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8981. Min Act: -0.1700
Data Index: 7752567 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8669. Min Act: -0.1700
Data Index: 8051612 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8669. Min Act: -0.1700
Data Index: 7847728 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8356. Min Act: -0.1700
Data Index: 7328082 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8044. Min Act: -0.1700
Data Index: 7365618 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8356. Min Act: -0.1700
Data Index: 4585354 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8044. Min Act: -0.1700
Data Index: 6051010 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3356. Min Range: -6.3356
Max Act: 5.8044. Min Act: -0.1700
Data Index: 2674556 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19