Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2165. Min Range: -6.2165
Max Act: 6.2165. Min Act: -0.1700
Data Index: 8013561 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2165. Min Range: -6.2165
Max Act: 6.1540. Min Act: -0.1700
Data Index: 3333592 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2165. Min Range: -6.2165
Max Act: 6.0602. Min Act: -0.1700
Data Index: 7507782 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2165. Min Range: -6.2165
Max Act: 6.0602. Min Act: -0.1700
Data Index: 8297237 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2165. Min Range: -6.2165
Max Act: 6.0290. Min Act: -0.1700
Data Index: 4549103 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2165. Min Range: -6.2165
Max Act: 6.0290. Min Act: -0.1700
Data Index: 3622223 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.9977. Min Act: -0.1700
Data Index: 5932887 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.9665. Min Act: -0.1700
Data Index: 1918836 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8727. Min Act: -0.1700
Data Index: 3692547 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8727. Min Act: -0.1700
Data Index: 2039396 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8727. Min Act: -0.1700
Data Index: 3037270 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.9040. Min Act: -0.1700
Data Index: 5125215 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8415. Min Act: -0.1700
Data Index: 2865887 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8415. Min Act: -0.1700
Data Index: 6309930 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8415. Min Act: -0.1700
Data Index: 7526023 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8102. Min Act: -0.1700
Data Index: 6517248 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.8102. Min Act: -0.1700
Data Index: 405429 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.7790. Min Act: -0.1700
Data Index: 3369127 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.7790. Min Act: -0.1700
Data Index: 4280166 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2165. Min Range: -6.2165
Max Act: 5.7790. Min Act: -0.1700
Data Index: 6160271 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19