Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5807 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5635. Min Range: -8.5635
Max Act: 8.5635. Min Act: -0.1700
Data Index: 5799138 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.8135. Min Act: -0.1700
Data Index: 917161 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.7510. Min Act: -0.1700
Data Index: 399661 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.7510. Min Act: -0.1700
Data Index: 2815070 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.7510. Min Act: -0.1700
Data Index: 2814120 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.7510. Min Act: -0.1700
Data Index: 3341053 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.7510. Min Act: -0.1700
Data Index: 5357935 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.6885. Min Act: -0.1700
Data Index: 4028532 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.6885. Min Act: -0.1700
Data Index: 6743002 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.6260. Min Act: -0.1700
Data Index: 5080381 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.6260. Min Act: -0.1700
Data Index: 3724823 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.5635. Min Act: -0.1700
Data Index: 3095035 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.5010. Min Act: -0.1700
Data Index: 3733175 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.5010. Min Act: -0.1700
Data Index: 2231599 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.5010. Min Act: -0.1700
Data Index: 4598358 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.5010. Min Act: -0.1700
Data Index: 5470660 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.4385. Min Act: -0.1700
Data Index: 63241 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.3447. Min Act: -0.1700
Data Index: 2499625 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.3135. Min Act: -0.1700
Data Index: 2415894 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5635. Min Range: -8.5635
Max Act: 7.3135. Min Act: -0.1700
Data Index: 8281684 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19