Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2394 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1416. Min Range: -4.1416
Max Act: 4.1416. Min Act: -0.1700
Data Index: 1873901 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1416. Min Range: -4.1416
Max Act: 4.1103. Min Act: -0.1700
Data Index: 4414220 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1416. Min Range: -4.1416
Max Act: 4.0791. Min Act: -0.1700
Data Index: 7858802 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1416. Min Range: -4.1416
Max Act: 4.0791. Min Act: -0.1700
Data Index: 1299239 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1416. Min Range: -4.1416
Max Act: 4.0166. Min Act: -0.1700
Data Index: 6226898 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1416. Min Range: -4.1416
Max Act: 4.0166. Min Act: -0.1700
Data Index: 5294536 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9853. Min Act: -0.1700
Data Index: 1180090 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1416. Min Range: -4.1416
Max Act: 4.0166. Min Act: -0.1700
Data Index: 1433996 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9853. Min Act: -0.1700
Data Index: 3151479 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9853. Min Act: -0.1700
Data Index: 8052986 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9853. Min Act: -0.1700
Data Index: 422319 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9540. Min Act: -0.1700
Data Index: 231379 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9540. Min Act: -0.1700
Data Index: 4037121 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9540. Min Act: -0.1700
Data Index: 2688161 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9853. Min Act: -0.1700
Data Index: 5173236 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9228. Min Act: -0.1700
Data Index: 125256 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9228. Min Act: -0.1700
Data Index: 6127106 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.8915. Min Act: -0.1700
Data Index: 3993300 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9228. Min Act: -0.1700
Data Index: 308163 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1416. Min Range: -4.1416
Max Act: 3.9228. Min Act: -0.1700
Data Index: 6732334 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19