Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.7670. Min Act: -0.1700
Data Index: 35299 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.7670. Min Act: -0.1700
Data Index: 4416029 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.6420. Min Act: -0.1700
Data Index: 5734797 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.5482. Min Act: -0.1700
Data Index: 57044 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.5170. Min Act: -0.1700
Data Index: 2478984 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.4545. Min Act: -0.1700
Data Index: 5138634 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.4545. Min Act: -0.1700
Data Index: 3910911 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.3920. Min Act: -0.1700
Data Index: 7308506 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.3920. Min Act: -0.1700
Data Index: 3951263 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.3920. Min Act: -0.1700
Data Index: 8107259 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.3920. Min Act: -0.1700
Data Index: 3272498 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.3920. Min Act: -0.1700
Data Index: 835766 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.3295. Min Act: -0.1700
Data Index: 4173212 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.2982. Min Act: -0.1700
Data Index: 3803241 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.2982. Min Act: -0.1700
Data Index: 161691 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.2670. Min Act: -0.1700
Data Index: 6560657 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.2670. Min Act: -0.1700
Data Index: 8509692 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.2670. Min Act: -0.1700
Data Index: 6376947 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.2670. Min Act: -0.1700
Data Index: 7276405 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7670. Min Range: -6.7670
Max Act: 6.2982. Min Act: -0.1700
Data Index: 2565234 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19