Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.8141. Min Act: -0.1700
Data Index: 8333731 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.7516. Min Act: -0.1700
Data Index: 4486390 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.7516. Min Act: -0.1700
Data Index: 6650654 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.7203. Min Act: -0.1700
Data Index: 8722069 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 2609539 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 4093640 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 839670 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 1625276 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 3076141 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 6115656 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6578. Min Act: -0.1700
Data Index: 3418068 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6266. Min Act: -0.1700
Data Index: 3834535 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6266. Min Act: -0.1700
Data Index: 7246024 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6266. Min Act: -0.1700
Data Index: 4258481 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.6266. Min Act: -0.1700
Data Index: 1678033 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.5953. Min Act: -0.1700
Data Index: 2228667 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.5641. Min Act: -0.1700
Data Index: 7583875 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.5953. Min Act: -0.1700
Data Index: 8438639 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.5953. Min Act: -0.1700
Data Index: 7168394 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8141. Min Range: -5.8141
Max Act: 5.5953. Min Act: -0.1700
Data Index: 4453963 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19