Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.9399. Min Act: -0.1700
Data Index: 6957384 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.6587. Min Act: -0.1700
Data Index: 1552181 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.6899. Min Act: -0.1700
Data Index: 7566932 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5962. Min Act: -0.1700
Data Index: 4321549 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5962. Min Act: -0.1700
Data Index: 6431161 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5962. Min Act: -0.1700
Data Index: 8629040 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5649. Min Act: -0.1700
Data Index: 3259132 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5649. Min Act: -0.1700
Data Index: 3452609 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5337. Min Act: -0.1700
Data Index: 8278960 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5024. Min Act: -0.1700
Data Index: 6873433 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4712. Min Act: -0.1700
Data Index: 1931945 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4712. Min Act: -0.1700
Data Index: 904638 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4712. Min Act: -0.1700
Data Index: 6806887 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.5024. Min Act: -0.1700
Data Index: 2243746 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4712. Min Act: -0.1700
Data Index: 6356674 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4087. Min Act: -0.1700
Data Index: 98805 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1219191 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4399. Min Act: -0.1700
Data Index: 5405397 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4087. Min Act: -0.1700
Data Index: 6162687 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9399. Min Range: -5.9399
Max Act: 5.4087. Min Act: -0.1700
Data Index: 4575668 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19