Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.7943. Min Act: -0.1700
Data Index: 3558149 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.7005. Min Act: -0.1700
Data Index: 8324287 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.5910. Min Act: -0.1700
Data Index: 4798985 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.5753. Min Act: -0.1700
Data Index: 1720506 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.5127. Min Act: -0.1700
Data Index: 303019 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.4344. Min Act: -0.1700
Data Index: 922088 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.4344. Min Act: -0.1700
Data Index: 3675472 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3717. Min Act: -0.1700
Data Index: 2916592 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3873. Min Act: -0.1700
Data Index: 5764620 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3717. Min Act: -0.1700
Data Index: 1271266 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3717. Min Act: -0.1700
Data Index: 1441141 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3717. Min Act: -0.1700
Data Index: 6272278 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3560. Min Act: -0.1700
Data Index: 419846 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3403. Min Act: -0.1700
Data Index: 8551173 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3089. Min Act: -0.1700
Data Index: 1743888 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3246. Min Act: -0.1700
Data Index: 7706709 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3246. Min Act: -0.1700
Data Index: 6840355 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3089. Min Act: -0.1700
Data Index: 535404 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3089. Min Act: -0.1700
Data Index: 5599317 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7943. Min Range: -3.7943
Max Act: 3.3089. Min Act: -0.1700
Data Index: 1210394 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19