Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2220 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.5157. Min Act: -0.1700
Data Index: 4615390 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.3595. Min Act: -0.1700
Data Index: 7266233 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.3595. Min Act: -0.1700
Data Index: 706533 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.1407. Min Act: -0.1700
Data Index: 3518923 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.1719. Min Act: -0.1700
Data Index: 1921931 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.1094. Min Act: -0.1700
Data Index: 2235391 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.1407. Min Act: -0.1700
Data Index: 718036 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.1094. Min Act: -0.1700
Data Index: 8409207 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0782. Min Act: -0.1700
Data Index: 7380237 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0782. Min Act: -0.1700
Data Index: 7632932 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.1094. Min Act: -0.1700
Data Index: 3110669 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0469. Min Act: -0.1700
Data Index: 6739065 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0469. Min Act: -0.1700
Data Index: 5195639 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0469. Min Act: -0.1700
Data Index: 2245362 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0469. Min Act: -0.1700
Data Index: 8610572 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0469. Min Act: -0.1700
Data Index: 1136181 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0157. Min Act: -0.1700
Data Index: 1792825 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0157. Min Act: -0.1700
Data Index: 6692008 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5157. Min Range: -4.5157
Max Act: 3.9844. Min Act: -0.1700
Data Index: 7612041 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5157. Min Range: -4.5157
Max Act: 4.0157. Min Act: -0.1700
Data Index: 7254123 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19