Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.7196. Min Act: -0.1700
Data Index: 843383 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.6258. Min Act: -0.1700
Data Index: 909726 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.6258. Min Act: -0.1700
Data Index: 4750614 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.6101. Min Act: -0.1700
Data Index: 1128338 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.6101. Min Act: -0.1700
Data Index: 2084370 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5945. Min Act: -0.1700
Data Index: 74373 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5945. Min Act: -0.1700
Data Index: 5205385 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5945. Min Act: -0.1700
Data Index: 6800488 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5945. Min Act: -0.1700
Data Index: 7656189 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5945. Min Act: -0.1700
Data Index: 4065836 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5788. Min Act: -0.1700
Data Index: 1072844 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5631. Min Act: -0.1700
Data Index: 3817177 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5631. Min Act: -0.1700
Data Index: 1406862 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5631. Min Act: -0.1700
Data Index: 1353075 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5475. Min Act: -0.1700
Data Index: 463164 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5318. Min Act: -0.1700
Data Index: 4350048 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5475. Min Act: -0.1700
Data Index: 6803815 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5475. Min Act: -0.1700
Data Index: 112216 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5475. Min Act: -0.1700
Data Index: 2945054 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7196. Min Range: -3.7196
Max Act: 3.5318. Min Act: -0.1700
Data Index: 2660879 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19