Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.7335. Min Act: -0.1700
Data Index: 5068682 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.4210. Min Act: -0.1700
Data Index: 8536517 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.4523. Min Act: -0.1700
Data Index: 425449 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.4210. Min Act: -0.1700
Data Index: 7646511 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.3273. Min Act: -0.1700
Data Index: 3448977 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.3273. Min Act: -0.1700
Data Index: 734111 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.2335. Min Act: -0.1700
Data Index: 6591556 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.2023. Min Act: -0.1700
Data Index: 6449325 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.2023. Min Act: -0.1700
Data Index: 880465 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.2023. Min Act: -0.1700
Data Index: 8224098 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.1710. Min Act: -0.1700
Data Index: 7909109 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.1710. Min Act: -0.1700
Data Index: 7830731 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.1710. Min Act: -0.1700
Data Index: 3770791 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.1710. Min Act: -0.1700
Data Index: 1069717 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.1398. Min Act: -0.1700
Data Index: 2465336 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.1398. Min Act: -0.1700
Data Index: 3632283 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.1398. Min Act: -0.1700
Data Index: 8469755 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.0773. Min Act: -0.1700
Data Index: 1527702 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.0460. Min Act: -0.1700
Data Index: 7122283 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7335. Min Range: -6.7335
Max Act: 6.0460. Min Act: -0.1700
Data Index: 2747236 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19