Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.5289. Min Act: -0.1700
Data Index: 3537249 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6130834 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.2789. Min Act: -0.1700
Data Index: 5287540 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.2477. Min Act: -0.1700
Data Index: 5405513 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.2164. Min Act: -0.1700
Data Index: 1160197 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.2164. Min Act: -0.1700
Data Index: 2854439 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.2164. Min Act: -0.1700
Data Index: 8698309 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.1852. Min Act: -0.1700
Data Index: 4236987 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.1852. Min Act: -0.1700
Data Index: 5783233 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.1852. Min Act: -0.1700
Data Index: 1888323 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6640544 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.1227. Min Act: -0.1700
Data Index: 2175396 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6358695 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.0914. Min Act: -0.1700
Data Index: 1972808 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.0914. Min Act: -0.1700
Data Index: 4635100 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.0914. Min Act: -0.1700
Data Index: 5014544 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.0914. Min Act: -0.1700
Data Index: 6197320 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.0602. Min Act: -0.1700
Data Index: 2049438 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.0602. Min Act: -0.1700
Data Index: 5815215 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5289. Min Range: -5.5289
Max Act: 5.0289. Min Act: -0.1700
Data Index: 5300250 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19