Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0384. Min Range: -9.0384
Max Act: 9.0384. Min Act: -0.1700
Data Index: 6062054 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0384. Min Range: -9.0384
Max Act: 9.0384. Min Act: -0.1700
Data Index: 8429317 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.9134. Min Act: -0.1700
Data Index: 4724144 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.7884. Min Act: -0.1700
Data Index: 4744787 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.6634. Min Act: -0.1700
Data Index: 2978130 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.6009. Min Act: -0.1700
Data Index: 2576115 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.6634. Min Act: -0.1700
Data Index: 1292653 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.6009. Min Act: -0.1700
Data Index: 840573 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.5384. Min Act: -0.1700
Data Index: 3930397 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.5384. Min Act: -0.1700
Data Index: 8710875 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.4759. Min Act: -0.1700
Data Index: 6825101 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.3509. Min Act: -0.1700
Data Index: 3596084 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.3509. Min Act: -0.1700
Data Index: 1101857 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.3509. Min Act: -0.1700
Data Index: 2686296 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.3509. Min Act: -0.1700
Data Index: 4761363 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.3509. Min Act: -0.1700
Data Index: 6692871 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.2884. Min Act: -0.1700
Data Index: 4761365 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.2259. Min Act: -0.1700
Data Index: 16970 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.2884. Min Act: -0.1700
Data Index: 2563776 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0384. Min Range: -9.0384
Max Act: 8.3509. Min Act: -0.1700
Data Index: 6718431 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19