Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0041. Min Range: -5.0041
Max Act: 5.0041. Min Act: -0.1700
Data Index: 4697172 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0041. Min Range: -5.0041
Max Act: 5.0041. Min Act: -0.1700
Data Index: 752412 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0041. Min Range: -5.0041
Max Act: 5.0041. Min Act: -0.1700
Data Index: 8755484 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.9728. Min Act: -0.1700
Data Index: 8332819 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.9416. Min Act: -0.1700
Data Index: 7577983 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.9416. Min Act: -0.1700
Data Index: 5444495 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.9728. Min Act: -0.1700
Data Index: 2695321 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.9103. Min Act: -0.1700
Data Index: 1203758 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8791. Min Act: -0.1700
Data Index: 8174467 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.9103. Min Act: -0.1700
Data Index: 3787546 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8791. Min Act: -0.1700
Data Index: 8393617 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8791. Min Act: -0.1700
Data Index: 1937840 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8791. Min Act: -0.1700
Data Index: 5512197 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8791. Min Act: -0.1700
Data Index: 5301579 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.9103. Min Act: -0.1700
Data Index: 8352308 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8791. Min Act: -0.1700
Data Index: 4864402 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8478. Min Act: -0.1700
Data Index: 6748150 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8478. Min Act: -0.1700
Data Index: 3860379 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8166. Min Act: -0.1700
Data Index: 7585276 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0041. Min Range: -5.0041
Max Act: 4.8478. Min Act: -0.1700
Data Index: 3992397 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19