Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.6303. Min Act: -0.1700
Data Index: 1259661 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5678. Min Act: -0.1700
Data Index: 1669702 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5678. Min Act: -0.1700
Data Index: 3680251 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5678. Min Act: -0.1700
Data Index: 7704157 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4989737 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.4741. Min Act: -0.1700
Data Index: 5804757 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.4741. Min Act: -0.1700
Data Index: 239801 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.4741. Min Act: -0.1700
Data Index: 7695226 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.4428. Min Act: -0.1700
Data Index: 1959891 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3803. Min Act: -0.1700
Data Index: 3862625 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3491. Min Act: -0.1700
Data Index: 1008949 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.3178. Min Act: -0.1700
Data Index: 32364 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2866. Min Act: -0.1700
Data Index: 5194724 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2866. Min Act: -0.1700
Data Index: 4918442 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2866. Min Act: -0.1700
Data Index: 7189691 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2866. Min Act: -0.1700
Data Index: 4250792 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2553. Min Act: -0.1700
Data Index: 4338213 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2553. Min Act: -0.1700
Data Index: 5954183 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2553. Min Act: -0.1700
Data Index: 1590256 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6303. Min Range: -6.6303
Max Act: 6.2241. Min Act: -0.1700
Data Index: 3290906 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19