Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1104. Min Range: -9.1104
Max Act: 9.1104. Min Act: -0.1700
Data Index: 7924568 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1104. Min Range: -9.1104
Max Act: 9.1104. Min Act: -0.1700
Data Index: 913174 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1104. Min Range: -9.1104
Max Act: 9.0479. Min Act: -0.1700
Data Index: 7486386 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.9854. Min Act: -0.1700
Data Index: 8089887 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1104. Min Range: -9.1104
Max Act: 9.0479. Min Act: -0.1700
Data Index: 2728197 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.8604. Min Act: -0.1700
Data Index: 3187245 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.8604. Min Act: -0.1700
Data Index: 809763 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.9229. Min Act: -0.1700
Data Index: 5868454 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.8604. Min Act: -0.1700
Data Index: 5055469 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.8604. Min Act: -0.1700
Data Index: 8663777 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7979. Min Act: -0.1700
Data Index: 1804271 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7979. Min Act: -0.1700
Data Index: 6582995 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7979. Min Act: -0.1700
Data Index: 6782569 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7979. Min Act: -0.1700
Data Index: 1091638 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7979. Min Act: -0.1700
Data Index: 7558205 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7979. Min Act: -0.1700
Data Index: 273753 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.6729. Min Act: -0.1700
Data Index: 3078925 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7354. Min Act: -0.1700
Data Index: 2047999 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7354. Min Act: -0.1700
Data Index: 526050 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1104. Min Range: -9.1104
Max Act: 8.7979. Min Act: -0.1700
Data Index: 6208979 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19