Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.9205. Min Act: -0.1700
Data Index: 1228551 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.8580. Min Act: -0.1700
Data Index: 6801429 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7643. Min Act: -0.1700
Data Index: 2293156 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7955. Min Act: -0.1700
Data Index: 3709711 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7643. Min Act: -0.1700
Data Index: 2664935 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7330. Min Act: -0.1700
Data Index: 8204190 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7955. Min Act: -0.1700
Data Index: 1865931 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7330. Min Act: -0.1700
Data Index: 3260043 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7018. Min Act: -0.1700
Data Index: 2935236 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7643. Min Act: -0.1700
Data Index: 8103085 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7643. Min Act: -0.1700
Data Index: 3140097 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7330. Min Act: -0.1700
Data Index: 2634278 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7330. Min Act: -0.1700
Data Index: 1884042 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7330. Min Act: -0.1700
Data Index: 291580 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7643. Min Act: -0.1700
Data Index: 5191351 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.7018. Min Act: -0.1700
Data Index: 909955 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.6705. Min Act: -0.1700
Data Index: 6125670 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.6705. Min Act: -0.1700
Data Index: 1613933 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.6705. Min Act: -0.1700
Data Index: 244660 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9205. Min Range: -6.9205
Max Act: 6.6705. Min Act: -0.1700
Data Index: 1670548 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19