Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.2690. Min Act: -0.1700
Data Index: 2196949 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.2690. Min Act: -0.1700
Data Index: 7072660 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.1752. Min Act: -0.1700
Data Index: 7036238 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.1752. Min Act: -0.1700
Data Index: 581100 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.1752. Min Act: -0.1700
Data Index: 7773819 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.1752. Min Act: -0.1700
Data Index: 3751760 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.1127. Min Act: -0.1700
Data Index: 751648 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.0815. Min Act: -0.1700
Data Index: 4857207 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.1127. Min Act: -0.1700
Data Index: 1347135 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.0815. Min Act: -0.1700
Data Index: 5349872 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.0502. Min Act: -0.1699
Data Index: 168615 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.9565. Min Act: -0.1700
Data Index: 7426334 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.8940. Min Act: -0.1700
Data Index: 8639148 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2690. Min Range: -5.2690
Max Act: 5.0190. Min Act: -0.1700
Data Index: 8639147 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.8315. Min Act: -0.1700
Data Index: 751647 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.8627. Min Act: -0.1700
Data Index: 1717592 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.8315. Min Act: -0.1700
Data Index: 4254417 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.8315. Min Act: -0.1700
Data Index: 7789424 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.8315. Min Act: -0.1700
Data Index: 7857899 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2690. Min Range: -5.2690
Max Act: 4.8002. Min Act: -0.1700
Data Index: 4254420 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19