Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1278. Min Range: -5.1278
Max Act: 5.1278. Min Act: -0.1700
Data Index: 2920949 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1278. Min Range: -5.1278
Max Act: 5.0653. Min Act: -0.1700
Data Index: 4950991 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1278. Min Range: -5.1278
Max Act: 5.0653. Min Act: -0.1700
Data Index: 1949592 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1278. Min Range: -5.1278
Max Act: 5.0965. Min Act: -0.1700
Data Index: 7314003 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1278. Min Range: -5.1278
Max Act: 5.0028. Min Act: -0.1700
Data Index: 1950962 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.9715. Min Act: -0.1700
Data Index: 3265927 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.9090. Min Act: -0.1700
Data Index: 3795462 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.9090. Min Act: -0.1700
Data Index: 7128017 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.9090. Min Act: -0.1700
Data Index: 780301 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.9090. Min Act: -0.1700
Data Index: 7481248 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8465. Min Act: -0.1700
Data Index: 160155 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8778. Min Act: -0.1700
Data Index: 8485343 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8778. Min Act: -0.1700
Data Index: 7729540 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8778. Min Act: -0.1700
Data Index: 365387 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.9090. Min Act: -0.1700
Data Index: 315759 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8778. Min Act: -0.1700
Data Index: 64355 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8778. Min Act: -0.1700
Data Index: 895115 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8465. Min Act: -0.1700
Data Index: 5634424 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8778. Min Act: -0.1700
Data Index: 5302345 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8465. Min Act: -0.1700
Data Index: 412726 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19