Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.5243. Min Act: -0.1700
Data Index: 6505748 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.4618. Min Act: -0.1700
Data Index: 976011 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.3368. Min Act: -0.1700
Data Index: 7420012 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.3055. Min Act: -0.1700
Data Index: 3315255 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.3055. Min Act: -0.1700
Data Index: 1976466 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2743. Min Act: -0.1700
Data Index: 1389761 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2743. Min Act: -0.1700
Data Index: 1306592 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2118. Min Act: -0.1700
Data Index: 3702130 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2118. Min Act: -0.1700
Data Index: 1475423 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2430. Min Act: -0.1700
Data Index: 6488538 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2430. Min Act: -0.1700
Data Index: 3532764 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2118. Min Act: -0.1700
Data Index: 6829049 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1805. Min Act: -0.1700
Data Index: 4347145 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2118. Min Act: -0.1700
Data Index: 4622996 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2118. Min Act: -0.1700
Data Index: 1013551 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1805. Min Act: -0.1700
Data Index: 4155979 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2118. Min Act: -0.1700
Data Index: 1804525 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1805. Min Act: -0.1700
Data Index: 1963347 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1493. Min Act: -0.1700
Data Index: 3952316 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1493. Min Act: -0.1700
Data Index: 7091864 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19