Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0857. Min Range: -7.0857
Max Act: 7.0857. Min Act: -0.1700
Data Index: 5098989 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0857. Min Range: -7.0857
Max Act: 7.0857. Min Act: -0.1700
Data Index: 5747537 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.9295. Min Act: -0.1700
Data Index: 5273210 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.8357. Min Act: -0.1700
Data Index: 5884894 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.8357. Min Act: -0.1700
Data Index: 4533307 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.7420. Min Act: -0.1700
Data Index: 4132477 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.7420. Min Act: -0.1700
Data Index: 6445234 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.7420. Min Act: -0.1700
Data Index: 2562649 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.7107. Min Act: -0.1700
Data Index: 4901954 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6795. Min Act: -0.1700
Data Index: 356088 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6795. Min Act: -0.1700
Data Index: 2347488 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6795. Min Act: -0.1700
Data Index: 1198910 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6795. Min Act: -0.1700
Data Index: 7838176 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6795. Min Act: -0.1700
Data Index: 5273209 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6795. Min Act: -0.1700
Data Index: 5950504 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6482. Min Act: -0.1700
Data Index: 8089707 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6795. Min Act: -0.1700
Data Index: 3704549 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.6170. Min Act: -0.1700
Data Index: 3381404 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.5857. Min Act: -0.1700
Data Index: 6765638 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0857. Min Range: -7.0857
Max Act: 6.5857. Min Act: -0.1700
Data Index: 1052768 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19