Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5326 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.4593. Min Act: -0.1700
Data Index: 8795987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.4122. Min Act: -0.1700
Data Index: 5619283 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3652. Min Act: -0.1700
Data Index: 5457304 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3652. Min Act: -0.1700
Data Index: 5289975 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3495. Min Act: -0.1700
Data Index: 3593692 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3495. Min Act: -0.1700
Data Index: 4233069 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3181. Min Act: -0.1700
Data Index: 4551474 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3181. Min Act: -0.1700
Data Index: 8311111 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3181. Min Act: -0.1700
Data Index: 5747804 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3024. Min Act: -0.1700
Data Index: 2566755 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3024. Min Act: -0.1700
Data Index: 3113583 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3024. Min Act: -0.1700
Data Index: 3952459 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2867. Min Act: -0.1700
Data Index: 1144966 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2867. Min Act: -0.1700
Data Index: 4365735 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2867. Min Act: -0.1700
Data Index: 6968182 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2867. Min Act: -0.1700
Data Index: 7428670 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2710. Min Act: -0.1700
Data Index: 3788009 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2710. Min Act: -0.1700
Data Index: 7264115 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2710. Min Act: -0.1700
Data Index: 7799631 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.2867. Min Act: -0.1700
Data Index: 7264130 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19