Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0071. Min Range: -5.0071
Max Act: 5.0071. Min Act: -0.1700
Data Index: 5901624 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.9446. Min Act: -0.1700
Data Index: 5328911 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.9446. Min Act: -0.1700
Data Index: 5394626 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.9446. Min Act: -0.1700
Data Index: 730425 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.9446. Min Act: -0.1700
Data Index: 6110457 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8821. Min Act: -0.1700
Data Index: 3905964 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8821. Min Act: -0.1700
Data Index: 8473230 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8509. Min Act: -0.1700
Data Index: 6647498 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8509. Min Act: -0.1700
Data Index: 2676451 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8509. Min Act: -0.1700
Data Index: 5626441 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8196. Min Act: -0.1700
Data Index: 615416 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8196. Min Act: -0.1700
Data Index: 2010265 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8509. Min Act: -0.1700
Data Index: 5590856 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8196. Min Act: -0.1700
Data Index: 3687542 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8196. Min Act: -0.1700
Data Index: 4672086 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7884. Min Act: -0.1700
Data Index: 1845648 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7884. Min Act: -0.1700
Data Index: 1374958 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.8196. Min Act: -0.1700
Data Index: 4059577 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7259. Min Act: -0.1700
Data Index: 699265 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0071. Min Range: -5.0071
Max Act: 4.7884. Min Act: -0.1700
Data Index: 4845589 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19