Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4521. Min Range: -7.4521
Max Act: 7.4521. Min Act: -0.1700
Data Index: 5784981 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4521. Min Range: -7.4521
Max Act: 7.4208. Min Act: -0.1700
Data Index: 2897715 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4521. Min Range: -7.4521
Max Act: 7.1708. Min Act: -0.1700
Data Index: 970287 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4521. Min Range: -7.4521
Max Act: 7.1396. Min Act: -0.1700
Data Index: 5300008 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4521. Min Range: -7.4521
Max Act: 7.0771. Min Act: -0.1700
Data Index: 7807906 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4521. Min Range: -7.4521
Max Act: 7.0771. Min Act: -0.1699
Data Index: 3266817 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4521. Min Range: -7.4521
Max Act: 7.0146. Min Act: -0.1700
Data Index: 8627106 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.9833. Min Act: -0.1700
Data Index: 6055914 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.8271. Min Act: -0.1700
Data Index: 5374025 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.8271. Min Act: -0.1700
Data Index: 3914670 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.7646. Min Act: -0.1700
Data Index: 6643860 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.7646. Min Act: -0.1700
Data Index: 2169547 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.7333. Min Act: -0.1700
Data Index: 7249523 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.7333. Min Act: -0.1700
Data Index: 4736247 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.7333. Min Act: -0.1700
Data Index: 4920146 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.6708. Min Act: -0.1700
Data Index: 1477506 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.7021. Min Act: -0.1700
Data Index: 3710182 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.6708. Min Act: -0.1700
Data Index: 1584207 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.6396. Min Act: -0.1700
Data Index: 7676118 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4521. Min Range: -7.4521
Max Act: 6.6708. Min Act: -0.1700
Data Index: 1315170 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19