Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4847 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1715. Min Range: -5.1715
Max Act: 5.1715. Min Act: -0.1700
Data Index: 7771496 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1715. Min Range: -5.1715
Max Act: 5.1402. Min Act: -0.1700
Data Index: 4852995 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1715. Min Range: -5.1715
Max Act: 5.0465. Min Act: -0.1700
Data Index: 1433308 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1715. Min Range: -5.1715
Max Act: 5.0777. Min Act: -0.1700
Data Index: 550999 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.8902. Min Act: -0.1700
Data Index: 6002671 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.8902. Min Act: -0.1700
Data Index: 2669221 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.8590. Min Act: -0.1700
Data Index: 8467148 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7965. Min Act: -0.1700
Data Index: 2551939 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7965. Min Act: -0.1700
Data Index: 1526179 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7340. Min Act: -0.1700
Data Index: 6002668 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7652. Min Act: -0.1700
Data Index: 1262075 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7340. Min Act: -0.1700
Data Index: 5539176 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7027. Min Act: -0.1700
Data Index: 209804 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7027. Min Act: -0.1700
Data Index: 3091671 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.6715. Min Act: -0.1700
Data Index: 6790507 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.6715. Min Act: -0.1700
Data Index: 7572542 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.7027. Min Act: -0.1700
Data Index: 1104443 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.6715. Min Act: -0.1700
Data Index: 3848845 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.6715. Min Act: -0.1700
Data Index: 3327400 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1715. Min Range: -5.1715
Max Act: 4.6402. Min Act: -0.1700
Data Index: 757108 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19