Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5696. Min Range: -7.5696
Max Act: 7.5696. Min Act: -0.1700
Data Index: 481461 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.9759. Min Act: -0.1700
Data Index: 5793358 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.9759. Min Act: -0.1700
Data Index: 1163342 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.8509. Min Act: -0.1700
Data Index: 7793144 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.8821. Min Act: -0.1700
Data Index: 4586684 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.7571. Min Act: -0.1700
Data Index: 3580655 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.7259. Min Act: -0.1700
Data Index: 1665540 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.6634. Min Act: -0.1700
Data Index: 1457794 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.6634. Min Act: -0.1700
Data Index: 8634260 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.6321. Min Act: -0.1700
Data Index: 6661473 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.6009. Min Act: -0.1700
Data Index: 6361454 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.5696. Min Act: -0.1700
Data Index: 3390633 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.5696. Min Act: -0.1700
Data Index: 6524580 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.5071. Min Act: -0.1700
Data Index: 6932875 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.4446. Min Act: -0.1700
Data Index: 768956 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.4446. Min Act: -0.1700
Data Index: 1028707 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.4759. Min Act: -0.1700
Data Index: 542652 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.4446. Min Act: -0.1700
Data Index: 4914886 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.4446. Min Act: -0.1700
Data Index: 4782886 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5696. Min Range: -7.5696
Max Act: 6.4446. Min Act: -0.1700
Data Index: 5977720 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19