Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.1657. Min Act: -0.1700
Data Index: 3323894 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.1345. Min Act: -0.1700
Data Index: 5291392 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.0720. Min Act: -0.1700
Data Index: 2088231 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.0720. Min Act: -0.1700
Data Index: 3588690 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.0720. Min Act: -0.1700
Data Index: 776778 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.0407. Min Act: -0.1700
Data Index: 2047267 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.0407. Min Act: -0.1700
Data Index: 1767145 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.0094. Min Act: -0.1700
Data Index: 7431268 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1657. Min Range: -4.1657
Max Act: 4.0094. Min Act: -0.1700
Data Index: 7078630 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.9469. Min Act: -0.1700
Data Index: 1906784 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.9782. Min Act: -0.1700
Data Index: 1961064 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.9157. Min Act: -0.1700
Data Index: 3171918 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.9157. Min Act: -0.1700
Data Index: 4747948 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.9157. Min Act: -0.1700
Data Index: 1486354 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.9157. Min Act: -0.1700
Data Index: 1183200 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.9157. Min Act: -0.1700
Data Index: 7383952 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.8844. Min Act: -0.1700
Data Index: 409569 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.8844. Min Act: -0.1700
Data Index: 7250598 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.8844. Min Act: -0.1700
Data Index: 4554391 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1657. Min Range: -4.1657
Max Act: 3.8531. Min Act: -0.1700
Data Index: 1605507 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19