Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4156. Min Range: -5.4156
Max Act: 5.4156. Min Act: -0.1700
Data Index: 3968152 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4156. Min Range: -5.4156
Max Act: 5.0718. Min Act: -0.1700
Data Index: 271790 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4156. Min Range: -5.4156
Max Act: 5.0406. Min Act: -0.1700
Data Index: 1123841 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.9156. Min Act: -0.1700
Data Index: 8106883 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1792374 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.8531. Min Act: -0.1700
Data Index: 4121267 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.8531. Min Act: -0.1700
Data Index: 2699753 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.7906. Min Act: -0.1700
Data Index: 8765502 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.7593. Min Act: -0.1700
Data Index: 8756979 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.7593. Min Act: -0.1700
Data Index: 7080470 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.7281. Min Act: -0.1700
Data Index: 702437 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6968. Min Act: -0.1700
Data Index: 1207171 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6968. Min Act: -0.1700
Data Index: 4295237 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6656. Min Act: -0.1700
Data Index: 4129943 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6656. Min Act: -0.1700
Data Index: 4908612 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6656. Min Act: -0.1700
Data Index: 6906164 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6343. Min Act: -0.1700
Data Index: 1312500 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6343. Min Act: -0.1700
Data Index: 1383280 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6343. Min Act: -0.1700
Data Index: 6838796 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4156. Min Range: -5.4156
Max Act: 4.6343. Min Act: -0.1700
Data Index: 5967268 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19