Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0178. Min Range: -7.0178
Max Act: 7.0178. Min Act: -0.1700
Data Index: 181374 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.5178. Min Act: -0.1700
Data Index: 3565981 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.4241. Min Act: -0.1700
Data Index: 7145832 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.3928. Min Act: -0.1700
Data Index: 2118265 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.2053. Min Act: -0.1700
Data Index: 3348523 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.1428. Min Act: -0.1700
Data Index: 5401852 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.0803. Min Act: -0.1700
Data Index: 7460482 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.0803. Min Act: -0.1700
Data Index: 573860 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.0491. Min Act: -0.1700
Data Index: 1455438 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.0491. Min Act: -0.1700
Data Index: 8280740 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.0178. Min Act: -0.1700
Data Index: 5497985 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0178. Min Range: -7.0178
Max Act: 6.0178. Min Act: -0.1700
Data Index: 3413447 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9866. Min Act: -0.1700
Data Index: 5375098 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9866. Min Act: -0.1700
Data Index: 3218886 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9866. Min Act: -0.1700
Data Index: 4234472 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9553. Min Act: -0.1700
Data Index: 3326359 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9553. Min Act: -0.1700
Data Index: 5594729 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9553. Min Act: -0.1700
Data Index: 8098051 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9241. Min Act: -0.1700
Data Index: 5997027 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0178. Min Range: -7.0178
Max Act: 5.9553. Min Act: -0.1700
Data Index: 6809120 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19