Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0285. Min Range: -7.0285
Max Act: 7.0285. Min Act: -0.1700
Data Index: 5906337 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.7785. Min Act: -0.1700
Data Index: 3136355 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.7160. Min Act: -0.1700
Data Index: 5585369 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.6222. Min Act: -0.1700
Data Index: 2449844 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.5910. Min Act: -0.1700
Data Index: 6114904 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.5597. Min Act: -0.1700
Data Index: 7741403 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.5285. Min Act: -0.1700
Data Index: 3779295 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.5597. Min Act: -0.1700
Data Index: 6291444 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.5285. Min Act: -0.1700
Data Index: 7690914 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.5285. Min Act: -0.1700
Data Index: 4333030 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.4972. Min Act: -0.1700
Data Index: 1736546 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.4347. Min Act: -0.1700
Data Index: 539200 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.4660. Min Act: -0.1700
Data Index: 3844388 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.4347. Min Act: -0.1700
Data Index: 8804665 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.4347. Min Act: -0.1700
Data Index: 2242161 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.4347. Min Act: -0.1700
Data Index: 6070980 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.3722. Min Act: -0.1700
Data Index: 3960268 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.3722. Min Act: -0.1700
Data Index: 3357661 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.3722. Min Act: -0.1700
Data Index: 2771984 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0285. Min Range: -7.0285
Max Act: 6.3410. Min Act: -0.1700
Data Index: 5986094 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19