Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4457. Min Range: -5.4457
Max Act: 5.4457. Min Act: -0.1700
Data Index: 5056172 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4457. Min Range: -5.4457
Max Act: 5.0082. Min Act: -0.1700
Data Index: 4368557 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.9770. Min Act: -0.1700
Data Index: 1616113 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.9457. Min Act: -0.1700
Data Index: 1931727 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.9457. Min Act: -0.1700
Data Index: 3085269 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.9145. Min Act: -0.1700
Data Index: 190194 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.8832. Min Act: -0.1700
Data Index: 7023775 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.8520. Min Act: -0.1700
Data Index: 910914 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.8520. Min Act: -0.1700
Data Index: 394370 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.8207. Min Act: -0.1700
Data Index: 7656152 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7895. Min Act: -0.1700
Data Index: 2573463 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7895. Min Act: -0.1700
Data Index: 6028770 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7895. Min Act: -0.1700
Data Index: 8350669 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7895. Min Act: -0.1700
Data Index: 1562333 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7895. Min Act: -0.1700
Data Index: 3039019 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7270. Min Act: -0.1700
Data Index: 7817787 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7582. Min Act: -0.1700
Data Index: 7725843 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7582. Min Act: -0.1700
Data Index: 2928206 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7582. Min Act: -0.1700
Data Index: 4493693 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4457. Min Range: -5.4457
Max Act: 4.7582. Min Act: -0.1700
Data Index: 7496576 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19