Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3796. Min Range: -4.3796
Max Act: 4.3796. Min Act: -0.1700
Data Index: 7801557 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3796. Min Range: -4.3796
Max Act: 4.2233. Min Act: -0.1700
Data Index: 4661138 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3796. Min Range: -4.3796
Max Act: 4.1295. Min Act: -0.1700
Data Index: 6753105 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3796. Min Range: -4.3796
Max Act: 4.0358. Min Act: -0.1700
Data Index: 6463930 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3796. Min Range: -4.3796
Max Act: 4.0670. Min Act: -0.1700
Data Index: 4965938 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.9420. Min Act: -0.1700
Data Index: 5146778 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.9420. Min Act: -0.1700
Data Index: 8369455 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.8794. Min Act: -0.1700
Data Index: 6031334 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.8794. Min Act: -0.1700
Data Index: 4159872 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.8794. Min Act: -0.1699
Data Index: 8614963 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.8482. Min Act: -0.1700
Data Index: 863640 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.8482. Min Act: -0.1700
Data Index: 2431291 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.8169. Min Act: -0.1700
Data Index: 7660388 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.8169. Min Act: -0.1700
Data Index: 4401224 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.7544. Min Act: -0.1700
Data Index: 204988 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.7856. Min Act: -0.1700
Data Index: 6062223 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.7856. Min Act: -0.1700
Data Index: 8521168 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.7856. Min Act: -0.1700
Data Index: 4984749 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.7544. Min Act: -0.1700
Data Index: 2416795 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3796. Min Range: -4.3796
Max Act: 3.7544. Min Act: -0.1700
Data Index: 8155049 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19