Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8869. Min Act: -0.1700
Data Index: 1913799 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8556. Min Act: -0.1700
Data Index: 8237665 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7931. Min Act: -0.1700
Data Index: 979802 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7619. Min Act: -0.1700
Data Index: 5993220 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.8244. Min Act: -0.1700
Data Index: 6512907 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7619. Min Act: -0.1700
Data Index: 794658 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7306. Min Act: -0.1700
Data Index: 8049003 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7619. Min Act: -0.1700
Data Index: 3311419 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7306. Min Act: -0.1700
Data Index: 45317 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.6994. Min Act: -0.1700
Data Index: 5177553 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.7306. Min Act: -0.1700
Data Index: 5480647 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.6681. Min Act: -0.1700
Data Index: 4830580 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.6369. Min Act: -0.1700
Data Index: 6665548 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.6681. Min Act: -0.1700
Data Index: 7171242 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.6369. Min Act: -0.1700
Data Index: 446232 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.6369. Min Act: -0.1700
Data Index: 6167526 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.5744. Min Act: -0.1700
Data Index: 1777517 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.6056. Min Act: -0.1700
Data Index: 5007748 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.5744. Min Act: -0.1700
Data Index: 532685 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8869. Min Range: -4.8869
Max Act: 4.5744. Min Act: -0.1700
Data Index: 5825356 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19