Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5156 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.5247. Min Act: -0.1700
Data Index: 4788043 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.5247. Min Act: -0.1700
Data Index: 2054226 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4934. Min Act: -0.1698
Data Index: 8440697 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4777. Min Act: -0.1700
Data Index: 8501335 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4777. Min Act: -0.1700
Data Index: 6063568 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4621. Min Act: -0.1700
Data Index: 181425 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4621. Min Act: -0.1700
Data Index: 4302247 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4777. Min Act: -0.1700
Data Index: 7070200 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4621. Min Act: -0.1700
Data Index: 624645 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4621. Min Act: -0.1700
Data Index: 3991003 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4464. Min Act: -0.1700
Data Index: 5069157 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4464. Min Act: -0.1700
Data Index: 5529784 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4464. Min Act: -0.1700
Data Index: 1339927 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4307. Min Act: -0.1700
Data Index: 6923992 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4307. Min Act: -0.1700
Data Index: 1705096 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4150. Min Act: -0.1700
Data Index: 5801521 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4150. Min Act: -0.1700
Data Index: 1214428 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4150. Min Act: -0.1700
Data Index: 6077429 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4150. Min Act: -0.1700
Data Index: 4431651 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5247. Min Range: -3.5247
Max Act: 3.4150. Min Act: -0.1700
Data Index: 6632606 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19