Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1444. Min Range: -4.1444
Max Act: 4.1444. Min Act: -0.1700
Data Index: 7459191 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1444. Min Range: -4.1444
Max Act: 4.1444. Min Act: -0.1700
Data Index: 1450307 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1444. Min Range: -4.1444
Max Act: 4.1444. Min Act: -0.1700
Data Index: 1053927 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1444. Min Range: -4.1444
Max Act: 4.0506. Min Act: -0.1700
Data Index: 3132311 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9881. Min Act: -0.1700
Data Index: 5588386 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1444. Min Range: -4.1444
Max Act: 4.0506. Min Act: -0.1700
Data Index: 5820503 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9881. Min Act: -0.1700
Data Index: 1562452 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 4571676 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9255. Min Act: -0.1700
Data Index: 7096827 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9255. Min Act: -0.1700
Data Index: 4458574 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 5249775 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 189188 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 7420481 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 8694472 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 4322952 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 5820504 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 5706030 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 4028122 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 4964511 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8317. Min Act: -0.1700
Data Index: 6168188 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19