Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.4636. Min Act: -0.1700
Data Index: 6558176 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.4011. Min Act: -0.1700
Data Index: 4232464 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.3386. Min Act: -0.1700
Data Index: 8818266 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.3386. Min Act: -0.1700
Data Index: 8736944 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.3386. Min Act: -0.1700
Data Index: 6849093 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.2761. Min Act: -0.1700
Data Index: 5913981 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.2761. Min Act: -0.1700
Data Index: 8281671 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.2761. Min Act: -0.1700
Data Index: 6339649 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.2761. Min Act: -0.1700
Data Index: 4308703 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.2136. Min Act: -0.1700
Data Index: 4344692 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.1511. Min Act: -0.1700
Data Index: 6181735 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0886. Min Act: -0.1700
Data Index: 1233848 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0886. Min Act: -0.1700
Data Index: 392892 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4636. Min Range: -8.4636
Max Act: 7.9636. Min Act: -0.1700
Data Index: 5294063 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0261. Min Act: -0.1700
Data Index: 7491921 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0261. Min Act: -0.1700
Data Index: 4837690 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0261. Min Act: -0.1700
Data Index: 8174163 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0261. Min Act: -0.1700
Data Index: 5894338 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0261. Min Act: -0.1700
Data Index: 6566885 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4636. Min Range: -8.4636
Max Act: 8.0261. Min Act: -0.1700
Data Index: 4776225 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19