Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1050 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.8365. Min Act: -0.1700
Data Index: 70245 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.7115. Min Act: -0.1700
Data Index: 5787285 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.6802. Min Act: -0.1700
Data Index: 6181015 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.7115. Min Act: -0.1700
Data Index: 3752214 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.5865. Min Act: -0.1700
Data Index: 8527562 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.5552. Min Act: -0.1700
Data Index: 6742481 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.4927. Min Act: -0.1700
Data Index: 5003019 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.4927. Min Act: -0.1700
Data Index: 5353914 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.3990. Min Act: -0.1700
Data Index: 4159235 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.4615. Min Act: -0.1700
Data Index: 7711925 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.3990. Min Act: -0.1700
Data Index: 967778 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.3365. Min Act: -0.1700
Data Index: 208678 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.3677. Min Act: -0.1700
Data Index: 3843184 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.3052. Min Act: -0.1700
Data Index: 5533535 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.3365. Min Act: -0.1700
Data Index: 5424314 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.2740. Min Act: -0.1700
Data Index: 2589158 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.2740. Min Act: -0.1700
Data Index: 4674315 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.2427. Min Act: -0.1700
Data Index: 3777067 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.2427. Min Act: -0.1700
Data Index: 7630661 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8365. Min Range: -6.8365
Max Act: 6.2427. Min Act: -0.1700
Data Index: 906062 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19