Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.2965. Min Act: -0.1700
Data Index: 1625916 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.2337. Min Act: -0.1700
Data Index: 5956529 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.2494. Min Act: -0.1700
Data Index: 202453 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.2180. Min Act: -0.1700
Data Index: 6844577 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.2180. Min Act: -0.1700
Data Index: 2544439 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1865. Min Act: -0.1700
Data Index: 2682225 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1865. Min Act: -0.1700
Data Index: 2887098 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1865. Min Act: -0.1700
Data Index: 489896 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1708. Min Act: -0.1700
Data Index: 4714725 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1550. Min Act: -0.1700
Data Index: 2305314 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1550. Min Act: -0.1700
Data Index: 2073979 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1393. Min Act: -0.1700
Data Index: 7261154 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1708. Min Act: -0.1700
Data Index: 1685172 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1550. Min Act: -0.1700
Data Index: 8340781 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1393. Min Act: -0.1700
Data Index: 1450243 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1393. Min Act: -0.1700
Data Index: 725685 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1235. Min Act: -0.1700
Data Index: 5565960 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1078. Min Act: -0.1700
Data Index: 8128306 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1235. Min Act: -0.1700
Data Index: 3088212 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2965. Min Range: -3.2965
Max Act: 3.1235. Min Act: -0.1700
Data Index: 7748988 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19