Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6097 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.7172. Min Act: -0.1700
Data Index: 1450675 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6860. Min Act: -0.1700
Data Index: 3004538 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6860. Min Act: -0.1700
Data Index: 3437034 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6860. Min Act: -0.1700
Data Index: 954732 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6860. Min Act: -0.1700
Data Index: 278897 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 2475255 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6547. Min Act: -0.1700
Data Index: 3109153 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6547. Min Act: -0.1700
Data Index: 5386358 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6547. Min Act: -0.1700
Data Index: 6697819 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 7225465 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 2154761 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6547. Min Act: -0.1700
Data Index: 1188068 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 6457900 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 2011250 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 6166686 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 6108824 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.5922. Min Act: -0.1700
Data Index: 154832 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 5957130 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 5222153 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7172. Min Range: -4.7172
Max Act: 4.6235. Min Act: -0.1700
Data Index: 4650898 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19