Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 77 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.9790. Min Act: -0.1700
Data Index: 3069374 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0415. Min Range: -9.0415
Max Act: 9.0415. Min Act: -0.1700
Data Index: 8723662 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.9165. Min Act: -0.1700
Data Index: 1763829 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.9165. Min Act: -0.1700
Data Index: 2202216 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.8540. Min Act: -0.1700
Data Index: 4759434 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7915. Min Act: -0.1700
Data Index: 7153632 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7915. Min Act: -0.1700
Data Index: 81388 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7915. Min Act: -0.1700
Data Index: 7313738 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7915. Min Act: -0.1700
Data Index: 726056 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7290. Min Act: -0.1700
Data Index: 1804093 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7290. Min Act: -0.1700
Data Index: 5296684 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7290. Min Act: -0.1700
Data Index: 6689829 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7290. Min Act: -0.1700
Data Index: 4211585 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7290. Min Act: -0.1700
Data Index: 8101426 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7915. Min Act: -0.1700
Data Index: 6432259 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7915. Min Act: -0.1700
Data Index: 888530 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.7290. Min Act: -0.1700
Data Index: 492486 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.6665. Min Act: -0.1700
Data Index: 6542356 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.6665. Min Act: -0.1700
Data Index: 2632285 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0415. Min Range: -9.0415
Max Act: 8.6665. Min Act: -0.1700
Data Index: 4922030 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19