Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4149 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8482. Min Range: -10.8482
Max Act: 10.8482. Min Act: -0.1700
Data Index: 7014990 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8482. Min Range: -10.8482
Max Act: 10.2232. Min Act: -0.1700
Data Index: 1315061 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.9732. Min Act: -0.1700
Data Index: 6248366 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.8482. Min Act: -0.1700
Data Index: 2613580 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.6607. Min Act: -0.1700
Data Index: 6493623 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.7232. Min Act: -0.1700
Data Index: 3439928 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.6607. Min Act: -0.1700
Data Index: 3293110 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.5982. Min Act: -0.1700
Data Index: 6207262 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.4107. Min Act: -0.1700
Data Index: 3988088 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.4107. Min Act: -0.1700
Data Index: 3308499 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.4107. Min Act: -0.1700
Data Index: 911925 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.4107. Min Act: -0.1700
Data Index: 8725867 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.4107. Min Act: -0.1700
Data Index: 5120151 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.4107. Min Act: -0.1700
Data Index: 1708653 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.3482. Min Act: -0.1700
Data Index: 6248336 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.3482. Min Act: -0.1700
Data Index: 3988087 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.3482. Min Act: -0.1700
Data Index: 2118323 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.3482. Min Act: -0.1700
Data Index: 5060309 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.3482. Min Act: -0.1700
Data Index: 8096130 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8482. Min Range: -10.8482
Max Act: 9.3482. Min Act: -0.1700
Data Index: 3697199 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19